{
  "schemaVersion": 1,
  "auditedAt": "2026-09-28T06:58:01+00:00",
  "scope": "Explicit native/default context; no automatic RoPE extrapolation or changes to performance support.",
  "models": [
    {
      "id": "01-ai/Yi-1.5-34B",
      "catalogId": "01-ai--yi-1.5-34b",
      "checkedAt": "2026-09-28T06:57:41+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-1.5-34B/blob/58a29f6dca2a4eda38821c086c29c1906114aabb/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "58a29f6dca2a4eda38821c086c29c1906114aabb",
      "sha256": "6bd316c688db290bb53251b1967d9b68f30b0364ecd738947facfe207b4bde42",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 20480,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 56,
        "num_hidden_layers": 60,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.2",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-1.5-34B-32K",
      "catalogId": "01-ai--yi-1.5-34b-32k",
      "checkedAt": "2026-09-28T06:57:41+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-1.5-34B-32K/blob/05a747585797c119aca9c49965003e99e9490b60/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "05a747585797c119aca9c49965003e99e9490b60",
      "sha256": "497f7cc27b497d3846db6d0b2a8f7a424a4e73e3388df0312ad6855df5fd963a",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 20480,
        "max_position_embeddings": 32768,
        "model_type": "llama",
        "num_attention_heads": 56,
        "num_hidden_layers": 60,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.1",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-1.5-34B-Chat",
      "catalogId": "01-ai--yi-1.5-34b-chat",
      "checkedAt": "2026-09-28T06:57:41+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-1.5-34B-Chat/blob/fa4ffba162f20948bf77c2a30eca952bf0812b7f/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "fa4ffba162f20948bf77c2a30eca952bf0812b7f",
      "sha256": "5aee47078b2c1ca2e784306df05d8ccf5cdf253694f05e0abdc5b023d34c5a38",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 20480,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 56,
        "num_hidden_layers": 60,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.0",
        "use_cache": false,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-1.5-34B-Chat-16K",
      "catalogId": "01-ai--yi-1.5-34b-chat-16k",
      "checkedAt": "2026-09-28T06:57:41+00:00",
      "previousMax": 16384,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-1.5-34B-Chat-16K/blob/ff74452e11f0f749ab872dc19b1dd3813c25c4d8/config.json",
      "max": 16384,
      "field": "max_position_embeddings",
      "revision": "ff74452e11f0f749ab872dc19b1dd3813c25c4d8",
      "sha256": "c84abd7746bbbf0816f9e91ba4d1bc748dff956963fad36e3fe0157648eb7b4e",
      "evidence": {
        "max_position_embeddings": 16384
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 20480,
        "max_position_embeddings": 16384,
        "model_type": "llama",
        "num_attention_heads": 56,
        "num_hidden_layers": 60,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.0",
        "use_cache": false,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-1.5-6B",
      "catalogId": "01-ai--yi-1.5-6b",
      "checkedAt": "2026-09-28T06:57:41+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-1.5-6B/blob/157a3d77ab5a8a8f079510eaa25169b547481f06/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "157a3d77ab5a8a8f079510eaa25169b547481f06",
      "sha256": "5ae838f29924daea6ea80b1d32c5bac32d8162570d37caef3e241c01054db668",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 4,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.2",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-1.5-6B-Chat",
      "catalogId": "01-ai--yi-1.5-6b-chat",
      "checkedAt": "2026-09-28T06:57:41+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-1.5-6B-Chat/blob/771924d1c83d67527d665913415d7086f11ea9c0/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "771924d1c83d67527d665913415d7086f11ea9c0",
      "sha256": "74e1d68c56a03b43b752997f600feff7d67a156f6affd2ae491aaac014cd8c17",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 4,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.0",
        "use_cache": false,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-1.5-9B",
      "catalogId": "01-ai--yi-1.5-9b",
      "checkedAt": "2026-09-28T06:57:42+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-1.5-9B/blob/80d5471b1eae28beae33e06eadbd4b48e74d4ce1/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "80d5471b1eae28beae33e06eadbd4b48e74d4ce1",
      "sha256": "d8b2e3bf56d638dc6932c1ba810c9ecf465d30611e0ca7a607e8a527bda720af",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 48,
        "num_key_value_heads": 4,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.2",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-1.5-9B-32K",
      "catalogId": "01-ai--yi-1.5-9b-32k",
      "checkedAt": "2026-09-28T06:57:42+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-1.5-9B-32K/blob/c0239dbc923b8a2b5ca849763bdd592d39c60850/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "c0239dbc923b8a2b5ca849763bdd592d39c60850",
      "sha256": "c33f1de19e514e87aa47adc9db199346a28f9f711c588f2188103f4a927a0c57",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 32768,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 48,
        "num_key_value_heads": 4,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.1",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-1.5-9B-Chat",
      "catalogId": "01-ai--yi-1.5-9b-chat",
      "checkedAt": "2026-09-28T06:57:42+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-1.5-9B-Chat/blob/1a0fc698cf883c4f5c325f026ca79f0ebd9955a5/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "1a0fc698cf883c4f5c325f026ca79f0ebd9955a5",
      "sha256": "a96597f583645c70ebda338eb3e3681c582eccc85b2a3e4b98eb031bce6e100d",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 48,
        "num_key_value_heads": 4,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.0",
        "use_cache": false,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-1.5-9B-Chat-16K",
      "catalogId": "01-ai--yi-1.5-9b-chat-16k",
      "checkedAt": "2026-09-28T06:57:42+00:00",
      "previousMax": 16384,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K/blob/2f8753bed95bd4fede3fd64f8305428620b4b212/config.json",
      "max": 16384,
      "field": "max_position_embeddings",
      "revision": "2f8753bed95bd4fede3fd64f8305428620b4b212",
      "sha256": "84818d0aa650bb8f668a8bae5e569c4f1d79b913d329f59c1536ab2544e88250",
      "evidence": {
        "max_position_embeddings": 16384
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 16384,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 48,
        "num_key_value_heads": 4,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.0",
        "use_cache": false,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-34B",
      "catalogId": "01-ai--yi-34b",
      "checkedAt": "2026-09-28T06:57:42+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-34B/blob/e1fa7c83283f2e1d5a12cb4adea37c3f829e28f8/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "e1fa7c83283f2e1d5a12cb4adea37c3f829e28f8",
      "sha256": "30cffdbbce0077bb474b491695c81fb5085470015a05808d352591501008f489",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 20480,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 56,
        "num_hidden_layers": 60,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.34.0",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-34B-200K",
      "catalogId": "01-ai--yi-34b-200k",
      "checkedAt": "2026-09-28T06:57:42+00:00",
      "previousMax": 200000,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-34B-200K/blob/e0ae1afac6b69f604556efd441ab4befafb2a835/config.json",
      "max": 200000,
      "field": "max_position_embeddings",
      "revision": "e0ae1afac6b69f604556efd441ab4befafb2a835",
      "sha256": "0653987de5f889d25bf53dffc53116d6b6af07b5b201c88440d597d3ae091b2e",
      "evidence": {
        "max_position_embeddings": 200000
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 20480,
        "max_position_embeddings": 200000,
        "model_type": "llama",
        "num_attention_heads": 56,
        "num_hidden_layers": 60,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.34.0",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-34B-Chat",
      "catalogId": "01-ai--yi-34b-chat",
      "checkedAt": "2026-09-28T06:57:42+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-34B-Chat/blob/cf02cb50f2a03dead2fe205766a1c5598a90bf80/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "cf02cb50f2a03dead2fe205766a1c5598a90bf80",
      "sha256": "282c0873e062d428a94c49ad0b5deffe4979c2f0d941fba242cbe4affa84a194",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 20480,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 56,
        "num_hidden_layers": 60,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.35.0",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-6B",
      "catalogId": "01-ai--yi-6b",
      "checkedAt": "2026-09-28T06:57:42+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-6B/blob/80080be87ec5a0103f643195f2d9003b8068941b/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "80080be87ec5a0103f643195f2d9003b8068941b",
      "sha256": "d83b4384262d880318a406a4ab80416eeaa2265c19e96e23bec2762d055351d9",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 4,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.34.0",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-6B-200K",
      "catalogId": "01-ai--yi-6b-200k",
      "checkedAt": "2026-09-28T06:57:42+00:00",
      "previousMax": 200000,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-6B-200K/blob/46b2762d8a78344292598f3ced6af746cec84bec/config.json",
      "max": 200000,
      "field": "max_position_embeddings",
      "revision": "46b2762d8a78344292598f3ced6af746cec84bec",
      "sha256": "592083f6c0921652e79b472b5f70ffeaf408363565a1765ca67e6713a7de3d17",
      "evidence": {
        "max_position_embeddings": 200000
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 200000,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 4,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.34.0",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-6B-Chat",
      "catalogId": "01-ai--yi-6b-chat",
      "checkedAt": "2026-09-28T06:57:42+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-6B-Chat/blob/2dbf63b0cb7bc493c0243502c6e6111a36e3a093/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "2dbf63b0cb7bc493c0243502c6e6111a36e3a093",
      "sha256": "75400cc9a254403e715cd40e007ba828d248dc073877231fe87e5dc70af3bc2b",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 4,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.35.0",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-9B",
      "catalogId": "01-ai--yi-9b",
      "checkedAt": "2026-09-28T06:57:42+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-9B/blob/7b7ca5cf23753f488859321e2439dc4bcbc0eca0/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "7b7ca5cf23753f488859321e2439dc4bcbc0eca0",
      "sha256": "3c9e44a68c882237a168dbccdf6be3cdf9eb755233c5630ac82fa19e71e68b44",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 48,
        "num_key_value_heads": 4,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 10000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.2",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-9B-200K",
      "catalogId": "01-ai--yi-9b-200k",
      "checkedAt": "2026-09-28T06:57:42+00:00",
      "previousMax": 262144,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-9B-200K/blob/8efb8b93f2afdd04ec6884352cd0ea727064a95b/config.json",
      "max": 262144,
      "field": "max_position_embeddings",
      "revision": "8efb8b93f2afdd04ec6884352cd0ea727064a95b",
      "sha256": "9136b85f08a208ad1be994d7d2b28c9ff1df5ac17b4f310b7744c554b72e03e1",
      "evidence": {
        "max_position_embeddings": 262144
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 262144,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 48,
        "num_key_value_heads": 4,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 10000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.2",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-Coder-1.5B-Chat",
      "catalogId": "01-ai--yi-coder-1.5b-chat",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-Coder-1.5B-Chat/blob/92fdd1b2f1539ac990e7f4a921db5601da2f0299/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "92fdd1b2f1539ac990e7f4a921db5601da2f0299",
      "sha256": "4d16f1187d5d1a43fdb1284b1749d674b62a8477583eb608df0e7fae934756ff",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 7,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 5504,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 16,
        "num_hidden_layers": 24,
        "num_key_value_heads": 16,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.0",
        "use_cache": false,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-Coder-9B",
      "catalogId": "01-ai--yi-coder-9b",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-Coder-9B/blob/bc6e63fd26a654ee42dba737a553310bfa01dc5d/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "bc6e63fd26a654ee42dba737a553310bfa01dc5d",
      "sha256": "3bbf94a552aa1ff002d62bc082aad2faa64d8190a0ecb1c5805fbcecceb4956d",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 48,
        "num_key_value_heads": 4,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.0",
        "use_cache": true,
        "vocab_size": 64000
      }
    },
    {
      "id": "01-ai/Yi-Coder-9B-Chat",
      "catalogId": "01-ai--yi-coder-9b-chat",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/01-ai/Yi-Coder-9B-Chat/blob/356a1f8d4e4a606d0b879e54191ca809918576b8/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "356a1f8d4e4a606d0b879e54191ca809918576b8",
      "sha256": "b1651532a93794fef9d1cddbe14aed5d40a96c04ab73c8708a0b125da425cf06",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 7,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 48,
        "num_key_value_heads": 4,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.0",
        "use_cache": false,
        "vocab_size": 64000
      }
    },
    {
      "id": "allenai/OLMo-2-0325-32B-Instruct",
      "catalogId": "allenai--olmo-2-0325-32b-instruct",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct/blob/b96024342a77a69aa0dda815c3454a671f477463/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "b96024342a77a69aa0dda815c3454a671f477463",
      "sha256": "e977b63b4196481a109089de5a4d4479eb18df70297d9c3e18d865cf5b098e51",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "_name_or_path": "allenai/open_instruct_dev",
        "architectures": [
          "Olmo2ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 100257,
        "eos_token_id": 100257,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 27648,
        "max_position_embeddings": 4096,
        "model_type": "olmo2",
        "num_attention_heads": 40,
        "num_hidden_layers": 64,
        "num_key_value_heads": 8,
        "pad_token_id": 100277,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 500000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.49.0",
        "use_cache": false,
        "vocab_size": 100352
      }
    },
    {
      "id": "allenai/OLMo-2-1124-13B-Instruct",
      "catalogId": "allenai--olmo-2-1124-13b-instruct",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/allenai/OLMo-2-1124-13B-Instruct/blob/3a5c85baefbb1896a54d56fe2e76c0395627ddf4/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "3a5c85baefbb1896a54d56fe2e76c0395627ddf4",
      "sha256": "10b1de896314ca2dbf5aeda0035113dbeaa34e086f2a29bb4944596a15f4861e",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "_name_or_path": "/weka/oe-adapt-default/costah/models/olmo2/1210_13b_gsm_beta_0.03_lr_3e-7_7470_checkpoints/step_180/",
        "architectures": [
          "Olmo2ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "eos_token_id": 100257,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 13824,
        "max_position_embeddings": 4096,
        "model_type": "olmo2",
        "num_attention_heads": 40,
        "num_hidden_layers": 40,
        "num_key_value_heads": 40,
        "pad_token_id": 100277,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 500000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.47.0.dev0",
        "use_cache": false,
        "vocab_size": 100352
      }
    },
    {
      "id": "allenai/OLMo-2-1124-7B-Instruct",
      "catalogId": "allenai--olmo-2-1124-7b-instruct",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/allenai/OLMo-2-1124-7B-Instruct/blob/470b1fba1ae01581f270116362ee4aa1b97f4c84/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "470b1fba1ae01581f270116362ee4aa1b97f4c84",
      "sha256": "ff8cc8709a229515676797ab6f343a09391041c9a8fbbc78bfec5be4c2e3664e",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "_name_or_path": "allenai/open_instruct_dev",
        "architectures": [
          "Olmo2ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "eos_token_id": 100257,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 4096,
        "model_type": "olmo2",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 32,
        "pad_token_id": 100277,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 500000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.47.0.dev0",
        "use_cache": false,
        "vocab_size": 100352
      }
    },
    {
      "id": "bigcode/starcoder2-15b",
      "catalogId": "bigcode--starcoder2-15b",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 16384,
      "status": "verified",
      "source": "https://huggingface.co/bigcode/starcoder2-15b/blob/46d44742909c03ac8cee08eb03fdebce02e193ec/config.json",
      "max": 16384,
      "field": "max_position_embeddings",
      "revision": "46d44742909c03ac8cee08eb03fdebce02e193ec",
      "sha256": "fdb2d6526092653e5f6f7af655926bf08161fadc165607eb41c2c840f5e5ca1d",
      "evidence": {
        "max_position_embeddings": 16384
      },
      "config": {
        "_name_or_path": "/aot/checkpoints/15b/config.json",
        "architectures": [
          "Starcoder2ForCausalLM"
        ],
        "attention_dropout": 0.1,
        "residual_dropout": 0.1,
        "embedding_dropout": 0.1,
        "bos_token_id": 0,
        "eos_token_id": 0,
        "hidden_act": "gelu_pytorch_tanh",
        "hidden_size": 6144,
        "initializer_range": 0.01275,
        "intermediate_size": 24576,
        "max_position_embeddings": 16384,
        "mlp_type": "default",
        "model_type": "starcoder2",
        "norm_epsilon": 1e-05,
        "norm_type": "layer_norm",
        "num_attention_heads": 48,
        "num_hidden_layers": 40,
        "num_key_value_heads": 4,
        "rope_theta": 100000,
        "sliding_window": 4096,
        "tie_word_embeddings": false,
        "torch_dtype": "float32",
        "transformers_version": "4.37.0.dev0",
        "use_bias": true,
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "bigcode/starcoder2-3b",
      "catalogId": "bigcode--starcoder2-3b",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 16384,
      "status": "verified",
      "source": "https://huggingface.co/bigcode/starcoder2-3b/blob/733247c55e3f73af49ce8e9c7949bf14af205928/config.json",
      "max": 16384,
      "field": "max_position_embeddings",
      "revision": "733247c55e3f73af49ce8e9c7949bf14af205928",
      "sha256": "636a8a48c05d5882e4467aacc1e2cc0dcff83be582f5658e3af172bda5e7d94e",
      "evidence": {
        "max_position_embeddings": 16384
      },
      "config": {
        "architectures": [
          "Starcoder2ForCausalLM"
        ],
        "attention_dropout": 0.1,
        "residual_dropout": 0.1,
        "embedding_dropout": 0.1,
        "bos_token_id": 0,
        "eos_token_id": 0,
        "hidden_act": "gelu_pytorch_tanh",
        "hidden_size": 3072,
        "initializer_range": 0.018042,
        "intermediate_size": 12288,
        "max_position_embeddings": 16384,
        "mlp_type": "default",
        "model_type": "starcoder2",
        "norm_epsilon": 1e-05,
        "norm_type": "layer_norm",
        "num_attention_heads": 24,
        "num_hidden_layers": 30,
        "num_key_value_heads": 2,
        "rope_theta": 999999.4420358813,
        "sliding_window": 4096,
        "transformers_version": "4.37.0.dev0",
        "use_bias": true,
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "bigcode/starcoder2-7b",
      "catalogId": "bigcode--starcoder2-7b",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 16384,
      "status": "verified",
      "source": "https://huggingface.co/bigcode/starcoder2-7b/blob/bb9afde76d7945da5745592525db122d4d729eb1/config.json",
      "max": 16384,
      "field": "max_position_embeddings",
      "revision": "bb9afde76d7945da5745592525db122d4d729eb1",
      "sha256": "af07df1e6ea8f9a1b74b8ada728e694c9e63db00fd71b1feccd0ae69d5292b9d",
      "evidence": {
        "max_position_embeddings": 16384
      },
      "config": {
        "activation_function": "gelu",
        "architectures": [
          "Starcoder2ForCausalLM"
        ],
        "attention_dropout": 0.1,
        "residual_dropout": 0.1,
        "embedding_dropout": 0.1,
        "attention_softmax_in_fp32": true,
        "bos_token_id": 0,
        "eos_token_id": 0,
        "hidden_act": "gelu_pytorch_tanh",
        "hidden_size": 4608,
        "initializer_range": 0.018042,
        "intermediate_size": 18432,
        "layer_norm_epsilon": 1e-05,
        "max_position_embeddings": 16384,
        "mlp_type": "default",
        "model_type": "starcoder2",
        "norm_epsilon": 1e-05,
        "norm_type": "layer_norm",
        "num_attention_heads": 36,
        "num_hidden_layers": 32,
        "num_key_value_heads": 4,
        "rope_theta": 1000000,
        "scale_attention_softmax_in_fp32": true,
        "scale_attn_weights": true,
        "sliding_window": 4096,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.0.dev0",
        "use_bias": true,
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "deepseek-ai/deepseek-coder-1.3b-instruct",
      "catalogId": "deepseek-ai--deepseek-coder-1.3b-instruct",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 16384,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-instruct/blob/e063262dac8366fc1f28a4da0ff3c50ea66259ca/config.json",
      "max": 16384,
      "field": "max_position_embeddings",
      "revision": "e063262dac8366fc1f28a4da0ff3c50ea66259ca",
      "sha256": "5e81a9fd94e640b412725ff4c6eef90b8862e526c93ca4f4c5179244bcf20550",
      "evidence": {
        "max_position_embeddings": 16384
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "bos_token_id": 32013,
        "eos_token_id": 32021,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 5504,
        "max_position_embeddings": 16384,
        "model_type": "llama",
        "num_attention_heads": 16,
        "num_hidden_layers": 24,
        "num_key_value_heads": 16,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "factor": 4.0,
          "type": "linear"
        },
        "rope_theta": 100000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.33.1",
        "use_cache": true,
        "vocab_size": 32256
      }
    },
    {
      "id": "deepseek-ai/deepseek-coder-6.7b-base",
      "catalogId": "deepseek-ai--deepseek-coder-6.7b-base",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 16384,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base/blob/ce2207a8bfef3ee92bd7dd4cc31c52cfa0046912/config.json",
      "max": 16384,
      "field": "max_position_embeddings",
      "revision": "ce2207a8bfef3ee92bd7dd4cc31c52cfa0046912",
      "sha256": "d6e95333839ce9726d6619ae3e055dd2cbf854f003bc45c426e0550860fa6448",
      "evidence": {
        "max_position_embeddings": 16384
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "bos_token_id": 32013,
        "eos_token_id": 32014,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 16384,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 32,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "factor": 4.0,
          "type": "linear"
        },
        "rope_theta": 100000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.34.1",
        "use_cache": true,
        "vocab_size": 32256
      }
    },
    {
      "id": "deepseek-ai/deepseek-coder-6.7b-instruct",
      "catalogId": "deepseek-ai--deepseek-coder-6.7b-instruct",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 16384,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct/blob/e5d64addd26a6a1db0f9b863abf6ee3141936807/config.json",
      "max": 16384,
      "field": "max_position_embeddings",
      "revision": "e5d64addd26a6a1db0f9b863abf6ee3141936807",
      "sha256": "a3a2ce1a623b367d3799fb0c1e1ba12d5b8fa51a8e7abba14d10dd3739cd73e4",
      "evidence": {
        "max_position_embeddings": 16384
      },
      "config": {
        "_name_or_path": "/3fs-jd/prod/deepseek/shared/zhuqihao/public_model/deepseek-coder-7b-instruct2",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "bos_token_id": 32013,
        "eos_token_id": 32021,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 16384,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 32,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "factor": 4.0,
          "type": "linear"
        },
        "rope_theta": 100000,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.34.1",
        "use_cache": true,
        "vocab_size": 32256
      }
    },
    {
      "id": "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
      "catalogId": "deepseek-ai--deepseek-coder-7b-instruct-v1.5",
      "checkedAt": "2026-09-28T06:57:43+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5/blob/2a050a4c59d687a85324d32e147517992117ed30/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "2a050a4c59d687a85324d32e147517992117ed30",
      "sha256": "b175cc978379b310371c8f4e16096595becfa0fda2ce3b45bf8931a1bcf03fd1",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "bos_token_id": 100000,
        "eos_token_id": 100015,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 30,
        "num_key_value_heads": 32,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.35.2",
        "use_cache": true,
        "vocab_size": 102400
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct",
      "catalogId": "deepseek-ai--deepseek-coder-v2-lite-instruct",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 163840,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct/blob/e434a23f91ba5b4923cf6c9d9a238eb4a08e3a11/config.json",
      "max": 163840,
      "field": "max_position_embeddings",
      "revision": "e434a23f91ba5b4923cf6c9d9a238eb4a08e3a11",
      "sha256": "5f2f880516f5cb5d17bbb0b0b78623dee45d84855de9c5a0e637eaf828267d2b",
      "evidence": {
        "max_position_embeddings": 163840
      },
      "config": {
        "architectures": [
          "DeepseekV2ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV2Config",
          "AutoModel": "modeling_deepseek.DeepseekV2Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
        },
        "aux_loss_alpha": 0.001,
        "bos_token_id": 100000,
        "eos_token_id": 100001,
        "first_k_dense_replace": 1,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 10944,
        "kv_lora_rank": 512,
        "max_position_embeddings": 163840,
        "model_type": "deepseek_v2",
        "moe_intermediate_size": 1408,
        "moe_layer_freq": 1,
        "n_group": 1,
        "n_routed_experts": 64,
        "n_shared_experts": 2,
        "norm_topk_prob": false,
        "num_attention_heads": 16,
        "num_experts_per_tok": 6,
        "num_hidden_layers": 27,
        "num_key_value_heads": 16,
        "pretraining_tp": 1,
        "q_lora_rank": null,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "beta_fast": 32,
          "beta_slow": 1,
          "factor": 40,
          "mscale": 0.707,
          "mscale_all_dim": 0.707,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "rope_theta": 10000,
        "routed_scaling_factor": 1.0,
        "scoring_func": "softmax",
        "seq_aux": true,
        "tie_word_embeddings": false,
        "topk_group": 1,
        "topk_method": "greedy",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.39.3",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 102400
      }
    },
    {
      "id": "deepseek-ai/deepseek-moe-16b-chat",
      "catalogId": "deepseek-ai--deepseek-moe-16b-chat",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/deepseek-moe-16b-chat/blob/eefd8ac7e8dc90e095129fe1a537d5e236b2e57c/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "eefd8ac7e8dc90e095129fe1a537d5e236b2e57c",
      "sha256": "856a97c4451cf43d1ef14483c98db6564767b3b3fca6384938b208b8ce1088b0",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "DeepseekForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekConfig",
          "AutoModel": "modeling_deepseek.DeepseekModel",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekForCausalLM"
        },
        "aux_loss_alpha": 0.001,
        "bos_token_id": 100000,
        "eos_token_id": 100001,
        "first_k_dense_replace": 1,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 10944,
        "max_position_embeddings": 4096,
        "model_type": "deepseek",
        "moe_intermediate_size": 1408,
        "moe_layer_freq": 1,
        "n_routed_experts": 64,
        "n_shared_experts": 2,
        "norm_topk_prob": false,
        "num_attention_heads": 16,
        "num_experts_per_tok": 6,
        "num_hidden_layers": 28,
        "num_key_value_heads": 16,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 10000,
        "scoring_func": "softmax",
        "seq_aux": true,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.36.2",
        "use_cache": true,
        "vocab_size": 102400
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-R1",
      "catalogId": "deepseek-ai--deepseek-r1",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 163840,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-R1/blob/56d4cbbb4d29f4355bab4b9a39ccb717a14ad5ad/config.json",
      "max": 163840,
      "field": "max_position_embeddings",
      "revision": "56d4cbbb4d29f4355bab4b9a39ccb717a14ad5ad",
      "sha256": "79ddea672a62e95d3f0be27be434375538e1988975971cffcf87c96c1de84a65",
      "evidence": {
        "max_position_embeddings": 163840
      },
      "config": {
        "architectures": [
          "DeepseekV3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV3Config",
          "AutoModel": "modeling_deepseek.DeepseekV3Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
        },
        "bos_token_id": 0,
        "eos_token_id": 1,
        "ep_size": 1,
        "first_k_dense_replace": 3,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 18432,
        "kv_lora_rank": 512,
        "max_position_embeddings": 163840,
        "model_type": "deepseek_v3",
        "moe_intermediate_size": 2048,
        "moe_layer_freq": 1,
        "n_group": 8,
        "n_routed_experts": 256,
        "n_shared_experts": 1,
        "norm_topk_prob": true,
        "num_attention_heads": 128,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 61,
        "num_key_value_heads": 128,
        "num_nextn_predict_layers": 1,
        "q_lora_rank": 1536,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "quantization_config": {
          "activation_scheme": "dynamic",
          "fmt": "e4m3",
          "quant_method": "fp8",
          "weight_block_size": [
            128,
            128
          ]
        },
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "beta_fast": 32,
          "beta_slow": 1,
          "factor": 40,
          "mscale": 1.0,
          "mscale_all_dim": 1.0,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "rope_theta": 10000,
        "routed_scaling_factor": 2.5,
        "scoring_func": "sigmoid",
        "tie_word_embeddings": false,
        "topk_group": 4,
        "topk_method": "noaux_tc",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.3",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 129280
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-R1-0528",
      "catalogId": "deepseek-ai--deepseek-r1-0528",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 163840,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/blob/4236a6af538feda4548eca9ab308586007567f52/config.json",
      "max": 163840,
      "field": "max_position_embeddings",
      "revision": "4236a6af538feda4548eca9ab308586007567f52",
      "sha256": "79ddea672a62e95d3f0be27be434375538e1988975971cffcf87c96c1de84a65",
      "evidence": {
        "max_position_embeddings": 163840
      },
      "config": {
        "architectures": [
          "DeepseekV3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV3Config",
          "AutoModel": "modeling_deepseek.DeepseekV3Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
        },
        "bos_token_id": 0,
        "eos_token_id": 1,
        "ep_size": 1,
        "first_k_dense_replace": 3,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 18432,
        "kv_lora_rank": 512,
        "max_position_embeddings": 163840,
        "model_type": "deepseek_v3",
        "moe_intermediate_size": 2048,
        "moe_layer_freq": 1,
        "n_group": 8,
        "n_routed_experts": 256,
        "n_shared_experts": 1,
        "norm_topk_prob": true,
        "num_attention_heads": 128,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 61,
        "num_key_value_heads": 128,
        "num_nextn_predict_layers": 1,
        "q_lora_rank": 1536,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "quantization_config": {
          "activation_scheme": "dynamic",
          "fmt": "e4m3",
          "quant_method": "fp8",
          "weight_block_size": [
            128,
            128
          ]
        },
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "beta_fast": 32,
          "beta_slow": 1,
          "factor": 40,
          "mscale": 1.0,
          "mscale_all_dim": 1.0,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "rope_theta": 10000,
        "routed_scaling_factor": 2.5,
        "scoring_func": "sigmoid",
        "tie_word_embeddings": false,
        "topk_group": 4,
        "topk_method": "noaux_tc",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.3",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 129280
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
      "catalogId": "deepseek-ai--deepseek-r1-0528-qwen3-8b",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/blob/6e8885a6ff5c1dc5201574c8fd700323f23c25fa/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "6e8885a6ff5c1dc5201574c8fd700323f23c25fa",
      "sha256": "1b1cbbba841c180e94192f7a25d2d97e21498fc1a0a0b4785942158af5eee183",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "Qwen3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 12288,
        "max_position_embeddings": 131072,
        "max_window_layers": 36,
        "model_type": "qwen3",
        "num_attention_heads": 32,
        "num_hidden_layers": 36,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "rope_type": "yarn",
          "factor": 4.0,
          "original_max_position_embeddings": 32768,
          "attn_factor": 0.8782488562869419
        },
        "rope_theta": 1000000,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
      "catalogId": "deepseek-ai--deepseek-r1-distill-llama-70b",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/blob/b1c0b44b4369b597ad119a196caf79a9c40e141e/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "b1c0b44b4369b597ad119a196caf79a9c40e141e",
      "sha256": "95ef9768e4741543dbfaf0c274f101855883ff338b235c99eca2b6a4f4abee12",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 128000,
        "eos_token_id": [
          128001,
          128008,
          128009
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 8192,
        "initializer_range": 0.02,
        "intermediate_size": 28672,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 64,
        "num_hidden_layers": 80,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "factor": 8.0,
          "high_freq_factor": 4.0,
          "low_freq_factor": 1.0,
          "original_max_position_embeddings": 8192,
          "rope_type": "llama3"
        },
        "rope_theta": 500000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.47.0.dev0",
        "use_cache": true,
        "vocab_size": 128256
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
      "catalogId": "deepseek-ai--deepseek-r1-distill-llama-8b",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/blob/6a6f4aa4197940add57724a7707d069478df56b1/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "6a6f4aa4197940add57724a7707d069478df56b1",
      "sha256": "54acfad3cffe057640904ca8a1e83525e6551c70c7a04c641f5a9eda0bbf64bd",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 128000,
        "eos_token_id": 128001,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "factor": 8.0,
          "low_freq_factor": 1.0,
          "high_freq_factor": 4.0,
          "original_max_position_embeddings": 8192,
          "rope_type": "llama3"
        },
        "rope_theta": 500000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.0.dev0",
        "use_cache": true,
        "vocab_size": 128256
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
      "catalogId": "deepseek-ai--deepseek-r1-distill-qwen-1.5b",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/blob/ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562",
      "sha256": "37bd455e9679d2959536270fed49d25cc7c290a64f6e52abb97c71345a9cee41",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151643,
        "hidden_act": "silu",
        "hidden_size": 1536,
        "initializer_range": 0.02,
        "intermediate_size": 8960,
        "max_position_embeddings": 131072,
        "max_window_layers": 21,
        "model_type": "qwen2",
        "num_attention_heads": 12,
        "num_hidden_layers": 28,
        "num_key_value_heads": 2,
        "rms_norm_eps": 1e-06,
        "rope_theta": 10000,
        "sliding_window": 4096,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.0",
        "use_cache": true,
        "use_mrope": false,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
      "catalogId": "deepseek-ai--deepseek-r1-distill-qwen-14b",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B/blob/1df8507178afcc1bef68cd8c393f61a886323761/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "1df8507178afcc1bef68cd8c393f61a886323761",
      "sha256": "fdb89460be9a6383451437cdf632a3e087522efa682265461f33507e7069f026",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151643,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 13824,
        "max_position_embeddings": 131072,
        "max_window_layers": 48,
        "model_type": "qwen2",
        "num_attention_heads": 40,
        "num_hidden_layers": 48,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000.0,
        "sliding_window": 131072,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 152064
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
      "catalogId": "deepseek-ai--deepseek-r1-distill-qwen-32b",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/711ad2ea6aa40cfca18895e8aca02ab92df1a746/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "711ad2ea6aa40cfca18895e8aca02ab92df1a746",
      "sha256": "2c003fe40b13d2d1f372254d77177ed753176150f3d424d1b5ad22ff1d78a987",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151643,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 27648,
        "max_position_embeddings": 131072,
        "max_window_layers": 64,
        "model_type": "qwen2",
        "num_attention_heads": 40,
        "num_hidden_layers": 64,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000.0,
        "sliding_window": 131072,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 152064
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
      "catalogId": "deepseek-ai--deepseek-r1-distill-qwen-7b",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/blob/916b56a44061fd5cd7d6a8fb632557ed4f724f60/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "916b56a44061fd5cd7d6a8fb632557ed4f724f60",
      "sha256": "8290d3c1e385e2616572eb6926f7e2745f901d1c13da95970326a8a73f6c379c",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151643,
        "hidden_act": "silu",
        "hidden_size": 3584,
        "initializer_range": 0.02,
        "intermediate_size": 18944,
        "max_position_embeddings": 131072,
        "max_window_layers": 28,
        "model_type": "qwen2",
        "num_attention_heads": 28,
        "num_hidden_layers": 28,
        "num_key_value_heads": 4,
        "rms_norm_eps": 1e-06,
        "rope_theta": 10000,
        "sliding_window": 4096,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.0",
        "use_cache": true,
        "use_mrope": false,
        "use_sliding_window": false,
        "vocab_size": 152064
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-V2",
      "catalogId": "deepseek-ai--deepseek-v2",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 163840,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-V2/blob/4461458f186c35188585855f28f77af5661ad489/config.json",
      "max": 163840,
      "field": "max_position_embeddings",
      "revision": "4461458f186c35188585855f28f77af5661ad489",
      "sha256": "36f572d2909bd108d73a814c585fd61afd56266960a13eb67c713e229d3435d1",
      "evidence": {
        "max_position_embeddings": 163840
      },
      "config": {
        "architectures": [
          "DeepseekV2ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV2Config",
          "AutoModel": "modeling_deepseek.DeepseekV2Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
        },
        "aux_loss_alpha": 0.001,
        "bos_token_id": 100000,
        "eos_token_id": 100001,
        "first_k_dense_replace": 1,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 12288,
        "kv_lora_rank": 512,
        "max_position_embeddings": 163840,
        "model_type": "deepseek_v2",
        "moe_intermediate_size": 1536,
        "moe_layer_freq": 1,
        "n_group": 8,
        "n_routed_experts": 160,
        "n_shared_experts": 2,
        "norm_topk_prob": false,
        "num_attention_heads": 128,
        "num_experts_per_tok": 6,
        "num_hidden_layers": 60,
        "num_key_value_heads": 128,
        "pretraining_tp": 1,
        "q_lora_rank": 1536,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "beta_fast": 32,
          "beta_slow": 1,
          "factor": 40,
          "mscale": 0.707,
          "mscale_all_dim": 0.707,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "rope_theta": 10000,
        "routed_scaling_factor": 16.0,
        "scoring_func": "softmax",
        "seq_aux": true,
        "tie_word_embeddings": false,
        "topk_group": 3,
        "topk_method": "group_limited_greedy",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.39.3",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 102400
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-V2-Lite",
      "catalogId": "deepseek-ai--deepseek-v2-lite",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 163840,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite/blob/604d5664dddd88a0433dbae533b7fe9472482de0/config.json",
      "max": 163840,
      "field": "max_position_embeddings",
      "revision": "604d5664dddd88a0433dbae533b7fe9472482de0",
      "sha256": "f346286b0f1c8b044252fd54cb4fa78b9fab6472a6e8bebb9edfe03d414ea03d",
      "evidence": {
        "max_position_embeddings": 163840
      },
      "config": {
        "architectures": [
          "DeepseekV2ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV2Config",
          "AutoModel": "modeling_deepseek.DeepseekV2Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
        },
        "aux_loss_alpha": 0.001,
        "bos_token_id": 100000,
        "eos_token_id": 100001,
        "first_k_dense_replace": 1,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 10944,
        "kv_lora_rank": 512,
        "max_position_embeddings": 163840,
        "model_type": "deepseek_v2",
        "moe_intermediate_size": 1408,
        "moe_layer_freq": 1,
        "n_group": 1,
        "n_routed_experts": 64,
        "n_shared_experts": 2,
        "norm_topk_prob": false,
        "num_attention_heads": 16,
        "num_experts_per_tok": 6,
        "num_hidden_layers": 27,
        "num_key_value_heads": 16,
        "pretraining_tp": 1,
        "q_lora_rank": null,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "beta_fast": 32,
          "beta_slow": 1,
          "factor": 40,
          "mscale": 0.707,
          "mscale_all_dim": 0.707,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "rope_theta": 10000,
        "routed_scaling_factor": 1.0,
        "scoring_func": "softmax",
        "seq_aux": true,
        "tie_word_embeddings": false,
        "topk_group": 1,
        "topk_method": "greedy",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.33.1",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 102400
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-V2-Lite-Chat",
      "catalogId": "deepseek-ai--deepseek-v2-lite-chat",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 163840,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat/blob/85864749cd611b4353ce1decdb286193298f64c7/config.json",
      "max": 163840,
      "field": "max_position_embeddings",
      "revision": "85864749cd611b4353ce1decdb286193298f64c7",
      "sha256": "f346286b0f1c8b044252fd54cb4fa78b9fab6472a6e8bebb9edfe03d414ea03d",
      "evidence": {
        "max_position_embeddings": 163840
      },
      "config": {
        "architectures": [
          "DeepseekV2ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV2Config",
          "AutoModel": "modeling_deepseek.DeepseekV2Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
        },
        "aux_loss_alpha": 0.001,
        "bos_token_id": 100000,
        "eos_token_id": 100001,
        "first_k_dense_replace": 1,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 10944,
        "kv_lora_rank": 512,
        "max_position_embeddings": 163840,
        "model_type": "deepseek_v2",
        "moe_intermediate_size": 1408,
        "moe_layer_freq": 1,
        "n_group": 1,
        "n_routed_experts": 64,
        "n_shared_experts": 2,
        "norm_topk_prob": false,
        "num_attention_heads": 16,
        "num_experts_per_tok": 6,
        "num_hidden_layers": 27,
        "num_key_value_heads": 16,
        "pretraining_tp": 1,
        "q_lora_rank": null,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "beta_fast": 32,
          "beta_slow": 1,
          "factor": 40,
          "mscale": 0.707,
          "mscale_all_dim": 0.707,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "rope_theta": 10000,
        "routed_scaling_factor": 1.0,
        "scoring_func": "softmax",
        "seq_aux": true,
        "tie_word_embeddings": false,
        "topk_group": 1,
        "topk_method": "greedy",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.33.1",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 102400
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-V3",
      "catalogId": "deepseek-ai--deepseek-v3",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 163840,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-V3/blob/e815299b0bcbac849fa540c768ef21845365c9eb/config.json",
      "max": 163840,
      "field": "max_position_embeddings",
      "revision": "e815299b0bcbac849fa540c768ef21845365c9eb",
      "sha256": "cbf0b95dc614de208a109bb5fd4e7eed11385e9c68411d2c17db5319443035d9",
      "evidence": {
        "max_position_embeddings": 163840
      },
      "config": {
        "architectures": [
          "DeepseekV3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV3Config",
          "AutoModel": "modeling_deepseek.DeepseekV3Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
        },
        "bos_token_id": 0,
        "eos_token_id": 1,
        "ep_size": 1,
        "first_k_dense_replace": 3,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 18432,
        "kv_lora_rank": 512,
        "max_position_embeddings": 163840,
        "model_type": "deepseek_v3",
        "moe_intermediate_size": 2048,
        "moe_layer_freq": 1,
        "n_group": 8,
        "n_routed_experts": 256,
        "n_shared_experts": 1,
        "norm_topk_prob": true,
        "num_attention_heads": 128,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 61,
        "num_key_value_heads": 128,
        "num_nextn_predict_layers": 1,
        "q_lora_rank": 1536,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "quantization_config": {
          "activation_scheme": "dynamic",
          "fmt": "e4m3",
          "quant_method": "fp8",
          "weight_block_size": [
            128,
            128
          ]
        },
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "beta_fast": 32,
          "beta_slow": 1,
          "factor": 40,
          "mscale": 1.0,
          "mscale_all_dim": 1.0,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "rope_theta": 10000,
        "routed_scaling_factor": 2.5,
        "scoring_func": "sigmoid",
        "tie_word_embeddings": false,
        "topk_group": 4,
        "topk_method": "noaux_tc",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.33.1",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 129280
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-V3-0324",
      "catalogId": "deepseek-ai--deepseek-v3-0324",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 163840,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-V3-0324/blob/e9b33add76883f293d6bf61f6bd89b497e80e335/config.json",
      "max": 163840,
      "field": "max_position_embeddings",
      "revision": "e9b33add76883f293d6bf61f6bd89b497e80e335",
      "sha256": "79ddea672a62e95d3f0be27be434375538e1988975971cffcf87c96c1de84a65",
      "evidence": {
        "max_position_embeddings": 163840
      },
      "config": {
        "architectures": [
          "DeepseekV3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV3Config",
          "AutoModel": "modeling_deepseek.DeepseekV3Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
        },
        "bos_token_id": 0,
        "eos_token_id": 1,
        "ep_size": 1,
        "first_k_dense_replace": 3,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 18432,
        "kv_lora_rank": 512,
        "max_position_embeddings": 163840,
        "model_type": "deepseek_v3",
        "moe_intermediate_size": 2048,
        "moe_layer_freq": 1,
        "n_group": 8,
        "n_routed_experts": 256,
        "n_shared_experts": 1,
        "norm_topk_prob": true,
        "num_attention_heads": 128,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 61,
        "num_key_value_heads": 128,
        "num_nextn_predict_layers": 1,
        "q_lora_rank": 1536,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "quantization_config": {
          "activation_scheme": "dynamic",
          "fmt": "e4m3",
          "quant_method": "fp8",
          "weight_block_size": [
            128,
            128
          ]
        },
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "beta_fast": 32,
          "beta_slow": 1,
          "factor": 40,
          "mscale": 1.0,
          "mscale_all_dim": 1.0,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "rope_theta": 10000,
        "routed_scaling_factor": 2.5,
        "scoring_func": "sigmoid",
        "tie_word_embeddings": false,
        "topk_group": 4,
        "topk_method": "noaux_tc",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.3",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 129280
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-V3.1",
      "catalogId": "deepseek-ai--deepseek-v3.1",
      "checkedAt": "2026-09-28T06:57:44+00:00",
      "previousMax": 163840,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1/blob/c0781d039fb7a1ba2abc4add0bdc293e92d2b8db/config.json",
      "max": 163840,
      "field": "max_position_embeddings",
      "revision": "c0781d039fb7a1ba2abc4add0bdc293e92d2b8db",
      "sha256": "3e5d192d745758862b0a3e6338ee181991db49933dbbd3185e1bde34944e7bad",
      "evidence": {
        "max_position_embeddings": 163840
      },
      "config": {
        "architectures": [
          "DeepseekV3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV3Config",
          "AutoModel": "modeling_deepseek.DeepseekV3Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
        },
        "bos_token_id": 0,
        "eos_token_id": 1,
        "ep_size": 1,
        "first_k_dense_replace": 3,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 18432,
        "kv_lora_rank": 512,
        "max_position_embeddings": 163840,
        "model_type": "deepseek_v3",
        "moe_intermediate_size": 2048,
        "moe_layer_freq": 1,
        "n_group": 8,
        "n_routed_experts": 256,
        "n_shared_experts": 1,
        "norm_topk_prob": true,
        "num_attention_heads": 128,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 61,
        "num_key_value_heads": 128,
        "num_nextn_predict_layers": 1,
        "q_lora_rank": 1536,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "quantization_config": {
          "activation_scheme": "dynamic",
          "fmt": "e4m3",
          "quant_method": "fp8",
          "weight_block_size": [
            128,
            128
          ],
          "scale_fmt": "ue8m0"
        },
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "beta_fast": 32,
          "beta_slow": 1,
          "factor": 40,
          "mscale": 1.0,
          "mscale_all_dim": 1.0,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "rope_theta": 10000,
        "routed_scaling_factor": 2.5,
        "scoring_func": "sigmoid",
        "tie_word_embeddings": false,
        "topk_group": 4,
        "topk_method": "noaux_tc",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.2",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 129280
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-V3.1-Base",
      "catalogId": "deepseek-ai--deepseek-v3.1-base",
      "checkedAt": "2026-09-28T06:57:45+00:00",
      "previousMax": 163840,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Base/blob/d3d4eafdc470de44bbf6f0a74f852eb522357be8/config.json",
      "max": 163840,
      "field": "max_position_embeddings",
      "revision": "d3d4eafdc470de44bbf6f0a74f852eb522357be8",
      "sha256": "3e5d192d745758862b0a3e6338ee181991db49933dbbd3185e1bde34944e7bad",
      "evidence": {
        "max_position_embeddings": 163840
      },
      "config": {
        "architectures": [
          "DeepseekV3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV3Config",
          "AutoModel": "modeling_deepseek.DeepseekV3Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
        },
        "bos_token_id": 0,
        "eos_token_id": 1,
        "ep_size": 1,
        "first_k_dense_replace": 3,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 18432,
        "kv_lora_rank": 512,
        "max_position_embeddings": 163840,
        "model_type": "deepseek_v3",
        "moe_intermediate_size": 2048,
        "moe_layer_freq": 1,
        "n_group": 8,
        "n_routed_experts": 256,
        "n_shared_experts": 1,
        "norm_topk_prob": true,
        "num_attention_heads": 128,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 61,
        "num_key_value_heads": 128,
        "num_nextn_predict_layers": 1,
        "q_lora_rank": 1536,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "quantization_config": {
          "activation_scheme": "dynamic",
          "fmt": "e4m3",
          "quant_method": "fp8",
          "weight_block_size": [
            128,
            128
          ],
          "scale_fmt": "ue8m0"
        },
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "beta_fast": 32,
          "beta_slow": 1,
          "factor": 40,
          "mscale": 1.0,
          "mscale_all_dim": 1.0,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "rope_theta": 10000,
        "routed_scaling_factor": 2.5,
        "scoring_func": "sigmoid",
        "tie_word_embeddings": false,
        "topk_group": 4,
        "topk_method": "noaux_tc",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.2",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 129280
      }
    },
    {
      "id": "deepseek-ai/DeepSeek-V3.1-Terminus",
      "catalogId": "deepseek-ai--deepseek-v3.1-terminus",
      "checkedAt": "2026-09-28T06:57:45+00:00",
      "previousMax": 163840,
      "status": "verified",
      "source": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus/blob/19510d6dc61f79dbd925bd51ee8a9081c509a4b6/config.json",
      "max": 163840,
      "field": "max_position_embeddings",
      "revision": "19510d6dc61f79dbd925bd51ee8a9081c509a4b6",
      "sha256": "c4238c5e765fa571f59443700af2d4ccdd9f2f62301b1f327722b486340f0d01",
      "evidence": {
        "max_position_embeddings": 163840
      },
      "config": {
        "architectures": [
          "DeepseekV3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attn_module_list_cfg": [],
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV3Config",
          "AutoModel": "modeling_deepseek.DeepseekV3Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
        },
        "bos_token_id": 0,
        "eos_token_id": 1,
        "ep_size": 1,
        "first_k_dense_replace": 3,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 18432,
        "kv_lora_rank": 512,
        "max_position_embeddings": 163840,
        "model_type": "deepseek_v3",
        "moe_intermediate_size": 2048,
        "moe_layer_freq": 1,
        "n_group": 8,
        "n_routed_experts": 256,
        "n_shared_experts": 1,
        "norm_topk_prob": true,
        "num_attention_heads": 128,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 61,
        "num_key_value_heads": 128,
        "num_nextn_predict_layers": 1,
        "q_lora_rank": 1536,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "quantization_config": {
          "activation_scheme": "dynamic",
          "fmt": "e4m3",
          "quant_method": "fp8",
          "weight_block_size": [
            128,
            128
          ]
        },
        "rms_norm_eps": 1e-06,
        "rope_scaling": {
          "beta_fast": 32,
          "beta_slow": 1,
          "factor": 40,
          "mscale": 1.0,
          "mscale_all_dim": 1.0,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "rope_theta": 10000,
        "routed_scaling_factor": 2.5,
        "scoring_func": "sigmoid",
        "tie_word_embeddings": false,
        "topk_group": 4,
        "topk_method": "noaux_tc",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.2",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 129280
      }
    },
    {
      "id": "google/gemma-1.1-2b-it",
      "catalogId": "google--gemma-1.1-2b-it",
      "checkedAt": "2026-09-28T06:57:45+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://github.com/google/gemma_pytorch/blob/014acb7ac4563a5f77c76d7ff98f31b568c16508/gemma/config.py",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "revision": "014acb7ac4563a5f77c76d7ff98f31b568c16508",
      "sha256": "43bcc8e024815e18e41045fd168509669ffc2af506061fa598db795e021dafd1",
      "field": "official-family-config.get_config_for_2b.max_position_embeddings",
      "evidence": {
        "function": "get_config_for_2b",
        "max_position_embeddings": 8192,
        "inheritedFromGemmaConfig": true
      }
    },
    {
      "id": "google/gemma-1.1-7b-it",
      "catalogId": "google--gemma-1.1-7b-it",
      "checkedAt": "2026-09-28T06:57:45+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://github.com/google/gemma_pytorch/blob/014acb7ac4563a5f77c76d7ff98f31b568c16508/gemma/config.py",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "revision": "014acb7ac4563a5f77c76d7ff98f31b568c16508",
      "sha256": "43bcc8e024815e18e41045fd168509669ffc2af506061fa598db795e021dafd1",
      "field": "official-family-config.get_config_for_7b.max_position_embeddings",
      "evidence": {
        "function": "get_config_for_7b",
        "max_position_embeddings": 8192,
        "inheritedFromGemmaConfig": true
      }
    },
    {
      "id": "google/gemma-2-27b",
      "catalogId": "google--gemma-2-27b",
      "checkedAt": "2026-09-28T06:57:45+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://github.com/google/gemma_pytorch/blob/014acb7ac4563a5f77c76d7ff98f31b568c16508/gemma/config.py",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "revision": "014acb7ac4563a5f77c76d7ff98f31b568c16508",
      "sha256": "43bcc8e024815e18e41045fd168509669ffc2af506061fa598db795e021dafd1",
      "field": "official-family-config.get_config_for_27b.max_position_embeddings",
      "evidence": {
        "function": "get_config_for_27b",
        "max_position_embeddings": 8192,
        "inheritedFromGemmaConfig": true
      }
    },
    {
      "id": "google/gemma-2-27b-it",
      "catalogId": "google--gemma-2-27b-it",
      "checkedAt": "2026-09-28T06:57:45+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://github.com/google/gemma_pytorch/blob/014acb7ac4563a5f77c76d7ff98f31b568c16508/gemma/config.py",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "revision": "014acb7ac4563a5f77c76d7ff98f31b568c16508",
      "sha256": "43bcc8e024815e18e41045fd168509669ffc2af506061fa598db795e021dafd1",
      "field": "official-family-config.get_config_for_27b.max_position_embeddings",
      "evidence": {
        "function": "get_config_for_27b",
        "max_position_embeddings": 8192,
        "inheritedFromGemmaConfig": true
      }
    },
    {
      "id": "google/gemma-2-2b",
      "catalogId": "google--gemma-2-2b",
      "checkedAt": "2026-09-28T06:57:45+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://github.com/google/gemma_pytorch/blob/014acb7ac4563a5f77c76d7ff98f31b568c16508/gemma/config.py",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "revision": "014acb7ac4563a5f77c76d7ff98f31b568c16508",
      "sha256": "43bcc8e024815e18e41045fd168509669ffc2af506061fa598db795e021dafd1",
      "field": "official-family-config.get_config_for_2b_v2.max_position_embeddings",
      "evidence": {
        "function": "get_config_for_2b_v2",
        "max_position_embeddings": 8192,
        "inheritedFromGemmaConfig": true
      }
    },
    {
      "id": "google/gemma-2-2b-it",
      "catalogId": "google--gemma-2-2b-it",
      "checkedAt": "2026-09-28T06:57:45+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://github.com/google/gemma_pytorch/blob/014acb7ac4563a5f77c76d7ff98f31b568c16508/gemma/config.py",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "revision": "014acb7ac4563a5f77c76d7ff98f31b568c16508",
      "sha256": "43bcc8e024815e18e41045fd168509669ffc2af506061fa598db795e021dafd1",
      "field": "official-family-config.get_config_for_2b_v2.max_position_embeddings",
      "evidence": {
        "function": "get_config_for_2b_v2",
        "max_position_embeddings": 8192,
        "inheritedFromGemmaConfig": true
      }
    },
    {
      "id": "google/gemma-2-9b",
      "catalogId": "google--gemma-2-9b",
      "checkedAt": "2026-09-28T06:57:46+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://github.com/google/gemma_pytorch/blob/014acb7ac4563a5f77c76d7ff98f31b568c16508/gemma/config.py",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "revision": "014acb7ac4563a5f77c76d7ff98f31b568c16508",
      "sha256": "43bcc8e024815e18e41045fd168509669ffc2af506061fa598db795e021dafd1",
      "field": "official-family-config.get_config_for_9b.max_position_embeddings",
      "evidence": {
        "function": "get_config_for_9b",
        "max_position_embeddings": 8192,
        "inheritedFromGemmaConfig": true
      }
    },
    {
      "id": "google/gemma-2-9b-it",
      "catalogId": "google--gemma-2-9b-it",
      "checkedAt": "2026-09-28T06:57:46+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://github.com/google/gemma_pytorch/blob/014acb7ac4563a5f77c76d7ff98f31b568c16508/gemma/config.py",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "revision": "014acb7ac4563a5f77c76d7ff98f31b568c16508",
      "sha256": "43bcc8e024815e18e41045fd168509669ffc2af506061fa598db795e021dafd1",
      "field": "official-family-config.get_config_for_9b.max_position_embeddings",
      "evidence": {
        "function": "get_config_for_9b",
        "max_position_embeddings": 8192,
        "inheritedFromGemmaConfig": true
      }
    },
    {
      "id": "google/gemma-2b",
      "catalogId": "google--gemma-2b",
      "checkedAt": "2026-09-28T06:57:46+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/google/gemma-2b",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "field": "model-card.training-context",
      "evidence": {
        "contextTokens": 8192
      },
      "revision": "9cf48e52b224239de00d483ec8eb84fb8d0f3a3a",
      "sha256": "5695e36030553b3e237ea429beefdb482c1af3539338be5d4ff7a7845761e504"
    },
    {
      "id": "google/gemma-2b-it",
      "catalogId": "google--gemma-2b-it",
      "checkedAt": "2026-09-28T06:57:46+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://github.com/google/gemma_pytorch/blob/014acb7ac4563a5f77c76d7ff98f31b568c16508/gemma/config.py",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "revision": "014acb7ac4563a5f77c76d7ff98f31b568c16508",
      "sha256": "43bcc8e024815e18e41045fd168509669ffc2af506061fa598db795e021dafd1",
      "field": "official-family-config.get_config_for_2b.max_position_embeddings",
      "evidence": {
        "function": "get_config_for_2b",
        "max_position_embeddings": 8192,
        "inheritedFromGemmaConfig": true
      }
    },
    {
      "id": "google/gemma-3-12b-it",
      "catalogId": "google--gemma-3-12b-it",
      "checkedAt": "2026-09-28T06:57:46+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/google/gemma-3-12b-it",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.input-context",
      "evidence": {
        "contextNotation": "128K",
        "size": "12b",
        "normalization": "K = 1024 tokens"
      },
      "revision": "96b6f1eccf38110c56df3a15bffe176da04bfd80",
      "sha256": "50a369feb24003f40a29f2b479086cf9a70f5198b5bbdce509f4e34f2bb7c441"
    },
    {
      "id": "google/gemma-3-1b-it",
      "catalogId": "google--gemma-3-1b-it",
      "checkedAt": "2026-09-28T06:57:46+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/google/gemma-3-1b-it",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 32768,
      "field": "model-card.input-context",
      "evidence": {
        "contextNotation": "32K",
        "size": "1b",
        "normalization": "K = 1024 tokens"
      },
      "revision": "dcc83ea841ab6100d6b47a070329e1ba4cf78752",
      "sha256": "57615d69ea6fb830dca884445395f9f5fbee56415eeb294531cc62168cc0162b"
    },
    {
      "id": "google/gemma-3-1b-pt",
      "catalogId": "google--gemma-3-1b-pt",
      "checkedAt": "2026-09-28T06:57:47+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/google/gemma-3-1b-pt",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 32768,
      "field": "model-card.input-context",
      "evidence": {
        "contextNotation": "32K",
        "size": "1b",
        "normalization": "K = 1024 tokens"
      },
      "revision": "fcf18a2a879aab110ca39f8bffbccd5d49d8eb29",
      "sha256": "ddc90a165182671174f0726f7297b2695a348d377d765945a3c670d85de9af0d"
    },
    {
      "id": "google/gemma-3-270m",
      "catalogId": "google--gemma-3-270m",
      "checkedAt": "2026-09-28T06:57:47+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/google/gemma-3-270m",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 32768,
      "field": "model-card.input-context",
      "evidence": {
        "contextNotation": "32K",
        "size": "270m",
        "normalization": "K = 1024 tokens"
      },
      "revision": "9b0cfec892e2bc2afd938c98eabe4e4a7b1e0ca1",
      "sha256": "27d5aea2a58720b797cc8fd4dd5190fcffa831730851e1b04e9278ae963ef938"
    },
    {
      "id": "google/gemma-3-270m-it",
      "catalogId": "google--gemma-3-270m-it",
      "checkedAt": "2026-09-28T06:57:47+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/google/gemma-3-270m-it",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 32768,
      "field": "model-card.input-context",
      "evidence": {
        "contextNotation": "32K",
        "size": "270m",
        "normalization": "K = 1024 tokens"
      },
      "revision": "ac82b4e820549b854eebf28ce6dedaf9fdfa17b3",
      "sha256": "f28476f12fa69efd505e14d532e635f279b22b24679b56802904804bc9a35e3b"
    },
    {
      "id": "google/gemma-3-27b-it",
      "catalogId": "google--gemma-3-27b-it",
      "checkedAt": "2026-09-28T06:57:48+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/google/gemma-3-27b-it",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.input-context",
      "evidence": {
        "contextNotation": "128K",
        "size": "27b",
        "normalization": "K = 1024 tokens"
      },
      "revision": "005ad3404e59d6023443cb575daa05336842228a",
      "sha256": "ee0ff96f956fefd278613cf5c80a83de41a28e253018a32c6420e8a6110613cf"
    },
    {
      "id": "google/gemma-3-4b-it",
      "catalogId": "google--gemma-3-4b-it",
      "checkedAt": "2026-09-28T06:57:48+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/google/gemma-3-4b-it",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.input-context",
      "evidence": {
        "contextNotation": "128K",
        "size": "4b",
        "normalization": "K = 1024 tokens"
      },
      "revision": "093f9f388b31de276ce2de164bdc2081324b9767",
      "sha256": "8881da25bab31312f9cc6d8179237b45dd6266e1976ebba605bf88be44740342"
    },
    {
      "id": "google/gemma-7b",
      "catalogId": "google--gemma-7b",
      "checkedAt": "2026-09-28T06:57:48+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/google/gemma-7b",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "field": "model-card.training-context",
      "evidence": {
        "contextTokens": 8192
      },
      "revision": "ff6768d9368919a1f025a54f9f5aa0ee591730bb",
      "sha256": "63eaccbf10f18a28c9bde25bec46e3765223c065ed3e43c255093bc63ea654d8"
    },
    {
      "id": "google/gemma-7b-it",
      "catalogId": "google--gemma-7b-it",
      "checkedAt": "2026-09-28T06:57:48+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://github.com/google/gemma_pytorch/blob/014acb7ac4563a5f77c76d7ff98f31b568c16508/gemma/config.py",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "revision": "014acb7ac4563a5f77c76d7ff98f31b568c16508",
      "sha256": "43bcc8e024815e18e41045fd168509669ffc2af506061fa598db795e021dafd1",
      "field": "official-family-config.get_config_for_7b.max_position_embeddings",
      "evidence": {
        "function": "get_config_for_7b",
        "max_position_embeddings": 8192,
        "inheritedFromGemmaConfig": true
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM-1.7B",
      "catalogId": "huggingfacetb--smollm-1.7b",
      "checkedAt": "2026-09-28T06:57:48+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM-1.7B/blob/d7449ff7241c863f3e8accc475155f0f97afa011/config.json",
      "max": 2048,
      "field": "max_position_embeddings",
      "revision": "d7449ff7241c863f3e8accc475155f0f97afa011",
      "sha256": "4939e564b1c7f19d4054dee9c026347f8519b491d7957dba2ad155888b99f584",
      "evidence": {
        "max_position_embeddings": 2048
      },
      "config": {
        "_name_or_path": "/fsx/loubna/checkpoints/cosmo2_1T/500000",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "max_position_embeddings": 2048,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 24,
        "num_key_value_heads": 32,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "float32",
        "transformers_version": "4.39.3",
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM-1.7B-Instruct",
      "catalogId": "huggingfacetb--smollm-1.7b-instruct",
      "checkedAt": "2026-09-28T06:57:49+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM-1.7B-Instruct/blob/69f49d9c36434d6a3f319dadc5bd3b812752b98b/config.json",
      "max": 2048,
      "field": "max_position_embeddings",
      "revision": "69f49d9c36434d6a3f319dadc5bd3b812752b98b",
      "sha256": "1efbcd16ed33838faecf09009a7b5cf6685d02ec0225fd25d1007229b8b2a39d",
      "evidence": {
        "max_position_embeddings": 2048
      },
      "config": {
        "_name_or_path": "HuggingFaceTB/cosmo2-1.7B-webinst-sc2",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "max_position_embeddings": 2048,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 24,
        "num_key_value_heads": 32,
        "pad_token_id": 2,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.42.3",
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM-135M",
      "catalogId": "huggingfacetb--smollm-135m",
      "checkedAt": "2026-09-28T06:57:49+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM-135M/blob/1d461723eec654e65efdc40cf49301c89c0c92f4/config.json",
      "max": 2048,
      "field": "max_position_embeddings",
      "revision": "1d461723eec654e65efdc40cf49301c89c0c92f4",
      "sha256": "a1fe6f43e20f7a6c6dbc6380222af9526b5cef262446391a281c038249e3e3b7",
      "evidence": {
        "max_position_embeddings": 2048
      },
      "config": {
        "_name_or_path": "/fsx/elie_bakouch/checkpoints/final-149M/600000",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 576,
        "initializer_range": 0.02,
        "intermediate_size": 1536,
        "max_position_embeddings": 2048,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 9,
        "num_hidden_layers": 30,
        "num_key_value_heads": 3,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.41.2",
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM-135M-Instruct",
      "catalogId": "huggingfacetb--smollm-135m-instruct",
      "checkedAt": "2026-09-28T06:57:49+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM-135M-Instruct/blob/fcc320f490e08fdb4b99d935b2c58d40bf35b0d0/config.json",
      "max": 2048,
      "field": "max_position_embeddings",
      "revision": "fcc320f490e08fdb4b99d935b2c58d40bf35b0d0",
      "sha256": "d89dd5a56c63ac3d2f6cea098ad8aebd94e5fc4e4060fb61cd7e0e8bd0b678bb",
      "evidence": {
        "max_position_embeddings": 2048
      },
      "config": {
        "_name_or_path": "HuggingFaceTB/SmolLM-135M",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 576,
        "initializer_range": 0.02,
        "intermediate_size": 1536,
        "max_position_embeddings": 2048,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 9,
        "num_hidden_layers": 30,
        "num_key_value_heads": 3,
        "pad_token_id": 2,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.42.3",
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM-360M",
      "catalogId": "huggingfacetb--smollm-360m",
      "checkedAt": "2026-09-28T06:57:49+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM-360M/blob/59f7ef243ee09a72cbc14cb054393a3e3b771d41/config.json",
      "max": 2048,
      "field": "max_position_embeddings",
      "revision": "59f7ef243ee09a72cbc14cb054393a3e3b771d41",
      "sha256": "fe61811079ce3d217e9ffda059c4880f26290e6ec428bb1b4454b7a60e0a231e",
      "evidence": {
        "max_position_embeddings": 2048
      },
      "config": {
        "_name_or_path": "/fsx/elie_bakouch/checkpoints/final-362M/600000",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 960,
        "initializer_range": 0.02,
        "intermediate_size": 2560,
        "max_position_embeddings": 2048,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 15,
        "num_hidden_layers": 32,
        "num_key_value_heads": 5,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.41.2",
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM-360M-Instruct",
      "catalogId": "huggingfacetb--smollm-360m-instruct",
      "checkedAt": "2026-09-28T06:57:49+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct/blob/73b7144f76331266f5f45d5642fd8da653583b13/config.json",
      "max": 2048,
      "field": "max_position_embeddings",
      "revision": "73b7144f76331266f5f45d5642fd8da653583b13",
      "sha256": "f69621f6439de2576bcf22374385ea4455b69b4d5a967f91e49289493bf62b7f",
      "evidence": {
        "max_position_embeddings": 2048
      },
      "config": {
        "_name_or_path": "HuggingFaceTB/SmolLM-360M",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 960,
        "initializer_range": 0.02,
        "intermediate_size": 2560,
        "max_position_embeddings": 2048,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 15,
        "num_hidden_layers": 32,
        "num_key_value_heads": 5,
        "pad_token_id": 2,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.42.3",
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM2-1.7B",
      "catalogId": "huggingfacetb--smollm2-1.7b",
      "checkedAt": "2026-09-28T06:57:49+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B/blob/effd688a12921b4cc83e3312b6feb579f70f9c71/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "effd688a12921b4cc83e3312b6feb579f70f9c71",
      "sha256": "33397f6af8090f7290f27ce6fb1cd23a95fd0915a5c648dfd10b6002aaf7fc48",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "max_position_embeddings": 8192,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 24,
        "num_key_value_heads": 32,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 130000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.1",
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
      "catalogId": "huggingfacetb--smollm2-1.7b-instruct",
      "checkedAt": "2026-09-28T06:57:49+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct/blob/31b70e2e869a7173562077fd711b654946d38674/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "31b70e2e869a7173562077fd711b654946d38674",
      "sha256": "994f50b16abb4ae00880baefe03c10260b5bd608d2bf586f7056ca05a534feea",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "max_position_embeddings": 8192,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 24,
        "num_key_value_heads": 32,
        "pad_token_id": 2,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 130000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.42.3",
        "transformers.js_config": {
          "dtype": "q4",
          "kv_cache_dtype": {
            "q4f16": "float16",
            "fp16": "float16"
          },
          "use_external_data_format": {
            "model.onnx": true,
            "model_fp16.onnx": true
          }
        },
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM2-1.7B-Instruct-16k",
      "catalogId": "huggingfacetb--smollm2-1.7b-instruct-16k",
      "checkedAt": "2026-09-28T06:57:49+00:00",
      "previousMax": 16384,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct-16k/blob/e6176739e9ab04f510137531200981d8401263f9/config.json",
      "max": 16384,
      "field": "max_position_embeddings",
      "revision": "e6176739e9ab04f510137531200981d8401263f9",
      "sha256": "75aaa7c7eeb3b2396bd8ea687f95d74dbe27bfd512c0216fa5433d9dd2e8c5d7",
      "evidence": {
        "max_position_embeddings": 16384
      },
      "config": {
        "_name_or_path": "/fsx/loubna/data/SmolLM2-1.7B-Instruct-rope500k",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "head_dim": 64,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "max_position_embeddings": 16384,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 24,
        "num_key_value_heads": 32,
        "pad_token_id": 2,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 500000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers.js_config": {
          "kv_cache_dtype": {
            "fp16": "float16",
            "q4f16": "float16"
          }
        },
        "transformers_version": "4.48.1",
        "use_cache": false,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM2-135M",
      "catalogId": "huggingfacetb--smollm2-135m",
      "checkedAt": "2026-09-28T06:57:49+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM2-135M/blob/93efa2f097d58c2a74874c7e644dbc9b0cee75a2/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "93efa2f097d58c2a74874c7e644dbc9b0cee75a2",
      "sha256": "1d556eab73b69c7f11f64c557a2f9c6f440bd4c6b89bb2584a6b498c92603843",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 576,
        "initializer_range": 0.041666666666666664,
        "intermediate_size": 1536,
        "is_llama_config": true,
        "max_position_embeddings": 8192,
        "model_type": "llama",
        "num_attention_heads": 9,
        "num_hidden_layers": 30,
        "num_key_value_heads": 3,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_interleaved": false,
        "rope_scaling": null,
        "rope_theta": 100000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.1",
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM2-135M-Instruct",
      "catalogId": "huggingfacetb--smollm2-135m-instruct",
      "checkedAt": "2026-09-28T06:57:49+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct/blob/12fd25f77366fa6b3b4b768ec3050bf629380bac/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "12fd25f77366fa6b3b4b768ec3050bf629380bac",
      "sha256": "8eb740e8bbe4cff95ea7b4588d17a2432deb16e8075bc5828ff7ba9be94d982a",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 576,
        "initializer_range": 0.041666666666666664,
        "intermediate_size": 1536,
        "is_llama_config": true,
        "max_position_embeddings": 8192,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 9,
        "num_hidden_layers": 30,
        "num_key_value_heads": 3,
        "pad_token_id": 2,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_interleaved": false,
        "rope_scaling": null,
        "rope_theta": 100000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.42.3",
        "transformers.js_config": {
          "kv_cache_dtype": {
            "q4f16": "float16",
            "fp16": "float16"
          }
        },
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM2-360M",
      "catalogId": "huggingfacetb--smollm2-360m",
      "checkedAt": "2026-09-28T06:57:49+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM2-360M/blob/f8027fd0eaeea54caa13c31d31b9fdc459c38b49/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "f8027fd0eaeea54caa13c31d31b9fdc459c38b49",
      "sha256": "34f7801487078de7e434e19162c497e5cc6ff397080e40e8586627cb68a5168a",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 960,
        "initializer_range": 0.02,
        "intermediate_size": 2560,
        "is_llama_config": true,
        "max_position_embeddings": 8192,
        "model_type": "llama",
        "num_attention_heads": 15,
        "num_hidden_layers": 32,
        "num_key_value_heads": 5,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_interleaved": false,
        "rope_scaling": null,
        "rope_theta": 100000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.1",
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM2-360M-Instruct",
      "catalogId": "huggingfacetb--smollm2-360m-instruct",
      "checkedAt": "2026-09-28T06:57:49+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct/blob/a10cc1512eabd3dde888204e902eca88bddb4951/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "a10cc1512eabd3dde888204e902eca88bddb4951",
      "sha256": "224f72354f10d617a359cc82ad15a3c96e866b9b2ffadb81997eeea9e88e22ee",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 960,
        "initializer_range": 0.02,
        "intermediate_size": 2560,
        "is_llama_config": true,
        "max_position_embeddings": 8192,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 15,
        "num_hidden_layers": 32,
        "num_key_value_heads": 5,
        "pad_token_id": 2,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_interleaved": false,
        "rope_scaling": null,
        "rope_theta": 100000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.42.3",
        "transformers.js_config": {
          "kv_cache_dtype": {
            "q4f16": "float16",
            "fp16": "float16"
          }
        },
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM3-3B",
      "catalogId": "huggingfacetb--smollm3-3b",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 65536,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM3-3B/blob/a07cc9a04f16550a088caea529712d1d335b0ac1/config.json",
      "max": 65536,
      "field": "max_position_embeddings",
      "revision": "a07cc9a04f16550a088caea529712d1d335b0ac1",
      "sha256": "c72b1031274ff4626e434d0019e88e95a767460135db9ee492eb80652b786af1",
      "evidence": {
        "max_position_embeddings": 65536
      },
      "config": {
        "architectures": [
          "SmolLM3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 128000,
        "eos_token_id": 128012,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "layer_types": [
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention",
          "full_attention"
        ],
        "max_position_embeddings": 65536,
        "max_window_layers": 28,
        "mlp_bias": false,
        "model_type": "smollm3",
        "no_rope_layer_interval": 4,
        "no_rope_layers": [
          1,
          1,
          1,
          0,
          1,
          1,
          1,
          0,
          1,
          1,
          1,
          0,
          1,
          1,
          1,
          0,
          1,
          1,
          1,
          0,
          1,
          1,
          1,
          0,
          1,
          1,
          1,
          0,
          1,
          1,
          1,
          0,
          1,
          1,
          1,
          0
        ],
        "num_attention_heads": 16,
        "num_hidden_layers": 36,
        "num_key_value_heads": 4,
        "pad_token_id": 128004,
        "pretraining_tp": 2,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "sliding_window": null,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.54.0.dev0",
        "use_cache": false,
        "use_sliding_window": false,
        "vocab_size": 128256
      }
    },
    {
      "id": "HuggingFaceTB/SmolLM3-3B-Base",
      "catalogId": "huggingfacetb--smollm3-3b-base",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 65536,
      "status": "verified",
      "source": "https://huggingface.co/HuggingFaceTB/SmolLM3-3B-Base/blob/d78a42f79198603e614095753484a04c10c2b940/config.json",
      "max": 65536,
      "field": "max_position_embeddings",
      "revision": "d78a42f79198603e614095753484a04c10c2b940",
      "sha256": "e8336e843aecb733691a043ad4209168e1730158b5e03c2672591cc946036a47",
      "evidence": {
        "max_position_embeddings": 65536
      },
      "config": {
        "architectures": [
          "SmolLM3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": null,
        "eos_token_id": 128001,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 65536,
        "model_type": "smollm3",
        "no_rope_layer_interval": 4,
        "num_attention_heads": 16,
        "num_hidden_layers": 36,
        "num_key_value_heads": 4,
        "pad_token_id": 128004,
        "pretraining_tp": 2,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "sliding_window": null,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.53.0.dev0",
        "transformers.js_config": {
          "use_external_data_format": true,
          "dtype": "q4",
          "kv_cache_dtype": {
            "q4f16": "float16",
            "fp16": "float16"
          }
        },
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 128256
      }
    },
    {
      "id": "ibm-granite/granite-3.0-1b-a400m-base",
      "catalogId": "ibm-granite--granite-3.0-1b-a400m-base",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-3.0-1b-a400m-base/blob/d91cbed802d85eb1b32374623331f6ab2b37403a/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "d91cbed802d85eb1b32374623331f6ab2b37403a",
      "sha256": "d281b6413c613a618863dc613f50a17fc4460a2a9882cf9c8e77c8329280c062",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "GraniteMoeForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.015625,
        "bos_token_id": 0,
        "embedding_multiplier": 12.0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 1024,
        "initializer_range": 0.02,
        "intermediate_size": 512,
        "logits_scaling": 6.0,
        "max_position_embeddings": 4096,
        "model_type": "granitemoe",
        "num_attention_heads": 16,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 24,
        "num_key_value_heads": 8,
        "num_local_experts": 32,
        "output_router_logits": false,
        "pad_token_id": 0,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 10000,
        "router_aux_loss_coef": 0.001,
        "tie_word_embeddings": true,
        "transformers_version": "4.45.0.dev0",
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "ibm-granite/granite-3.0-1b-a400m-instruct",
      "catalogId": "ibm-granite--granite-3.0-1b-a400m-instruct",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-3.0-1b-a400m-instruct/blob/ffec3c35bdfd97a06f0b4cd5fcc92cd9b1584445/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "ffec3c35bdfd97a06f0b4cd5fcc92cd9b1584445",
      "sha256": "ca4bb3a5c1bdef988ab413e0d731640446da65316e4ed16de3666cd96ecc3a0b",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "GraniteMoeForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.015625,
        "bos_token_id": 0,
        "embedding_multiplier": 12.0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 1024,
        "initializer_range": 0.02,
        "intermediate_size": 512,
        "logits_scaling": 6.0,
        "max_position_embeddings": 4096,
        "model_type": "granitemoe",
        "num_attention_heads": 16,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 24,
        "num_key_value_heads": 8,
        "num_local_experts": 32,
        "output_router_logits": false,
        "pad_token_id": 0,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 10000,
        "router_aux_loss_coef": 0.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.0.dev0",
        "use_cache": true,
        "vocab_size": 49155
      }
    },
    {
      "id": "ibm-granite/granite-3.0-8b-base",
      "catalogId": "ibm-granite--granite-3.0-8b-base",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-3.0-8b-base/blob/4fad7f8ad56393dcef4e34e37a35962bd091f320/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "4fad7f8ad56393dcef4e34e37a35962bd091f320",
      "sha256": "0fd71a7bc48f02a0fcafa3ab00f2f102cb64ad8289bfa54cfa42f3a0d136f116",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.1,
        "attention_multiplier": 0.0078125,
        "bos_token_id": 0,
        "embedding_multiplier": 12.0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 12800,
        "logits_scaling": 16.0,
        "max_position_embeddings": 4096,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000,
        "tie_word_embeddings": true,
        "transformers_version": "4.45.0.dev0",
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "ibm-granite/granite-3.0-8b-instruct",
      "catalogId": "ibm-granite--granite-3.0-8b-instruct",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-3.0-8b-instruct/blob/5af56291a1c6ca9056df597aab0cff53edabddb0/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "5af56291a1c6ca9056df597aab0cff53edabddb0",
      "sha256": "af3bcffc517ada48e1a5ac6cd38b452b044704a4e278c2af087da7e9e0f2e297",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.1,
        "attention_multiplier": 0.0078125,
        "bos_token_id": 0,
        "embedding_multiplier": 12.0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 12800,
        "logits_scaling": 16.0,
        "max_position_embeddings": 4096,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.0.dev0",
        "use_cache": true,
        "vocab_size": 49155
      }
    },
    {
      "id": "ibm-granite/granite-3.1-1b-a400m-instruct",
      "catalogId": "ibm-granite--granite-3.1-1b-a400m-instruct",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-3.1-1b-a400m-instruct/blob/0da7a48b0276d500ce5922fd2b33944091fc6c09/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "0da7a48b0276d500ce5922fd2b33944091fc6c09",
      "sha256": "f1b64813debfabeb9cc20f1a13ed8248da6774fe54e532d19912d4b3f2ab335d",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteMoeForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.015625,
        "bos_token_id": 0,
        "embedding_multiplier": 12.0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 1024,
        "initializer_range": 0.02,
        "intermediate_size": 512,
        "logits_scaling": 6.0,
        "max_position_embeddings": 131072,
        "model_type": "granitemoe",
        "num_attention_heads": 16,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 24,
        "num_key_value_heads": 8,
        "num_local_experts": 32,
        "output_router_logits": false,
        "pad_token_id": 0,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1500000.0,
        "router_aux_loss_coef": 0.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.47.0",
        "use_cache": true,
        "vocab_size": 49155
      }
    },
    {
      "id": "ibm-granite/granite-3.1-2b-instruct",
      "catalogId": "ibm-granite--granite-3.1-2b-instruct",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-3.1-2b-instruct/blob/bbc2aed595bd38bd770263dc3ab831db9794441d/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "bbc2aed595bd38bd770263dc3ab831db9794441d",
      "sha256": "5832d470c0ebb05cb0760fe05f80fa3e67ba42ba2d0a549bd36c6807f8d18672",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.1,
        "attention_multiplier": 0.015625,
        "bos_token_id": 0,
        "embedding_multiplier": 12.0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "logits_scaling": 8.0,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.47.0",
        "use_cache": true,
        "vocab_size": 49155
      }
    },
    {
      "id": "ibm-granite/granite-3.1-3b-a800m-instruct",
      "catalogId": "ibm-granite--granite-3.1-3b-a800m-instruct",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-3.1-3b-a800m-instruct/blob/a02780686e08a03fe0d2679a293b5c74a90efa89/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "a02780686e08a03fe0d2679a293b5c74a90efa89",
      "sha256": "b431a9f3059a59f60ca3e30b345fab29ea5789523c89e798b61ac96a201f2279",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteMoeForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.015625,
        "bos_token_id": 0,
        "embedding_multiplier": 12.0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 1536,
        "initializer_range": 0.02,
        "intermediate_size": 512,
        "logits_scaling": 6.0,
        "max_position_embeddings": 131072,
        "model_type": "granitemoe",
        "num_attention_heads": 24,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "num_local_experts": 40,
        "output_router_logits": false,
        "pad_token_id": 0,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 10000000.0,
        "router_aux_loss_coef": 0.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.47.0",
        "use_cache": true,
        "vocab_size": 49155
      }
    },
    {
      "id": "ibm-granite/granite-3.1-8b-instruct",
      "catalogId": "ibm-granite--granite-3.1-8b-instruct",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-3.1-8b-instruct/blob/4009206d5fc95d2e65a7b7633e159d6e97e25d35/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "4009206d5fc95d2e65a7b7633e159d6e97e25d35",
      "sha256": "03c19685d37a17a541641fb17fa40ba371d1d892e87334d3068d90e8f296a365",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.1,
        "attention_multiplier": 0.0078125,
        "bos_token_id": 0,
        "embedding_multiplier": 12.0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 12800,
        "logits_scaling": 16.0,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.47.0",
        "use_cache": true,
        "vocab_size": 49155
      }
    },
    {
      "id": "ibm-granite/granite-3.2-8b-instruct",
      "catalogId": "ibm-granite--granite-3.2-8b-instruct",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-3.2-8b-instruct/blob/610d8c6ee9c84ce51f6dfd7bc5c0215d95d49695/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "610d8c6ee9c84ce51f6dfd7bc5c0215d95d49695",
      "sha256": "f6b1eca4bc5f8f5e67ab2c88a842fc0dd1e5f148de6f3fd14349ccdade07df8b",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.1,
        "attention_multiplier": 0.0078125,
        "bos_token_id": 0,
        "embedding_multiplier": 12.0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 12800,
        "logits_scaling": 16.0,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.47.0",
        "use_cache": true,
        "vocab_size": 49155
      }
    },
    {
      "id": "ibm-granite/granite-3.3-2b-instruct",
      "catalogId": "ibm-granite--granite-3.3-2b-instruct",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-3.3-2b-instruct/blob/707f574c62054322f6b5b04b6d075f0a8f05e0f0/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "707f574c62054322f6b5b04b6d075f0a8f05e0f0",
      "sha256": "9202d328d8368958aab7dad89a8e6aa35c250b3a2eedd2d8850ee0bcceca65f6",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.015625,
        "bos_token_id": 0,
        "embedding_multiplier": 12.0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "logits_scaling": 8.0,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.49.0",
        "use_cache": true,
        "vocab_size": 49159
      }
    },
    {
      "id": "ibm-granite/granite-3.3-8b-instruct",
      "catalogId": "ibm-granite--granite-3.3-8b-instruct",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-3.3-8b-instruct/blob/51dd4bc2ade4059a6bd87649d68aa11e4fb2529b/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "51dd4bc2ade4059a6bd87649d68aa11e4fb2529b",
      "sha256": "1313edf0d39dcf7ed35a072d341ec11b516c12acc4267cfb6d248c6bdcdddcb7",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.0078125,
        "bos_token_id": 0,
        "embedding_multiplier": 12.0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 12800,
        "logits_scaling": 16.0,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.49.0",
        "use_cache": true,
        "vocab_size": 49159
      }
    },
    {
      "id": "ibm-granite/granite-3b-code-base-2k",
      "catalogId": "ibm-granite--granite-3b-code-base-2k",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-3b-code-base-2k/blob/b67f3dabc0b6d00ae477bd76732c7f3458a2caf3/config.json",
      "max": 2048,
      "field": "max_position_embeddings",
      "revision": "b67f3dabc0b6d00ae477bd76732c7f3458a2caf3",
      "sha256": "bdc265c2e79f1c6b6c0f4f25313e0d1cc936e0fd4e1e082bb26f65a4bd0fa557",
      "evidence": {
        "max_position_embeddings": 2048
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.1,
        "bos_token_id": 0,
        "eos_token_id": 0,
        "hidden_act": "silu",
        "hidden_size": 2560,
        "initializer_range": 0.02,
        "intermediate_size": 10240,
        "max_position_embeddings": 2048,
        "mlp_bias": true,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 32,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.41.0.dev0",
        "use_cache": true,
        "vocab_size": 49152
      }
    },
    {
      "id": "ibm-granite/granite-4.1-30b",
      "catalogId": "ibm-granite--granite-4.1-30b",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-4.1-30b/blob/4fae6278f7132abf5e971f9de49ebbad09c54cce/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "4fae6278f7132abf5e971f9de49ebbad09c54cce",
      "sha256": "384f1935366f0b0f9c3b4296ef7cd64a08288e15cfe16c40d13101a98ab713f4",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.0078125,
        "bos_token_id": 100257,
        "embedding_multiplier": 12.0,
        "eos_token_id": 100257,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "init_method": "mup",
        "initializer_range": 0.1,
        "intermediate_size": 32768,
        "logits_scaling": 16.0,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 32,
        "num_hidden_layers": 64,
        "num_key_value_heads": 8,
        "pad_token_id": 100256,
        "residual_multiplier": 0.175,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 50000000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.53.3",
        "use_cache": true,
        "vocab_size": 100352
      }
    },
    {
      "id": "ibm-granite/granite-4.1-3b",
      "catalogId": "ibm-granite--granite-4.1-3b",
      "checkedAt": "2026-09-28T06:57:50+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-4.1-3b/blob/c0650403e44e78ec0262dab1c90914c65b196c4e/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "c0650403e44e78ec0262dab1c90914c65b196c4e",
      "sha256": "9a0e589b69e7d3ad9fb9fb2c844aa7d7156e052cb7ea4211de7de48ab7c8525c",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.015625,
        "bos_token_id": 100257,
        "embedding_multiplier": 12.0,
        "eos_token_id": 100257,
        "hidden_act": "silu",
        "hidden_size": 2560,
        "initializer_range": 0.1,
        "intermediate_size": 8192,
        "logits_scaling": 10.0,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 40,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 100256,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.53.3",
        "use_cache": true,
        "vocab_size": 100352
      }
    },
    {
      "id": "ibm-granite/granite-4.1-3b-base",
      "catalogId": "ibm-granite--granite-4.1-3b-base",
      "checkedAt": "2026-09-28T06:57:51+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-4.1-3b-base/blob/dacb9cb9157bec98e99b09f285c92a4d58405c96/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "dacb9cb9157bec98e99b09f285c92a4d58405c96",
      "sha256": "9a0e589b69e7d3ad9fb9fb2c844aa7d7156e052cb7ea4211de7de48ab7c8525c",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.015625,
        "bos_token_id": 100257,
        "embedding_multiplier": 12.0,
        "eos_token_id": 100257,
        "hidden_act": "silu",
        "hidden_size": 2560,
        "initializer_range": 0.1,
        "intermediate_size": 8192,
        "logits_scaling": 10.0,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 40,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 100256,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.53.3",
        "use_cache": true,
        "vocab_size": 100352
      }
    },
    {
      "id": "ibm-granite/granite-4.1-8b",
      "catalogId": "ibm-granite--granite-4.1-8b",
      "checkedAt": "2026-09-28T06:57:51+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-4.1-8b/blob/1504002f650e656a0a3789d99574df12e3e94ed0/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "1504002f650e656a0a3789d99574df12e3e94ed0",
      "sha256": "dea9d856cb57018117fe2fe3366f37cb4aa39424890061db2c0045a6a4efbda0",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.0078125,
        "bos_token_id": 100257,
        "embedding_multiplier": 12.0,
        "eos_token_id": 100257,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.1,
        "intermediate_size": 12800,
        "logits_scaling": 16.0,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 100256,
        "residual_multiplier": 0.22,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000000,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.53.3",
        "use_cache": true,
        "vocab_size": 100352
      }
    },
    {
      "id": "ibm-granite/granite-4.2-30b",
      "catalogId": "ibm-granite--granite-4.2-30b",
      "checkedAt": "2026-09-28T06:57:51+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-4.2-30b/blob/9e668ce1c538387ef24d3644e9b0606647762636/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "9e668ce1c538387ef24d3644e9b0606647762636",
      "sha256": "82c834ac6bf6a2ecbf9801b49c3fb927008df24ea415c35e931b6091cab21277",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.0078125,
        "bos_token_id": 100283,
        "dtype": "bfloat16",
        "embedding_multiplier": 1.0,
        "eos_token_id": 100257,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.1,
        "intermediate_size": 32768,
        "logits_scaling": 1.0,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 32,
        "num_hidden_layers": 64,
        "num_key_value_heads": 8,
        "pad_token_id": 100257,
        "residual_multiplier": 1.0,
        "rms_norm_eps": 1e-05,
        "rope_parameters": {
          "rope_theta": 50000000,
          "rope_type": "default"
        },
        "rope_scaling": null,
        "rope_theta": 50000000,
        "tie_word_embeddings": false,
        "transformers_version": "4.57.1",
        "use_cache": true,
        "vocab_size": 100352,
        "torch_dtype": "bfloat16"
      }
    },
    {
      "id": "ibm-granite/granite-4.2-3b",
      "catalogId": "ibm-granite--granite-4.2-3b",
      "checkedAt": "2026-09-28T06:57:51+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-4.2-3b/blob/e459acceac81e5fe67c07d9cfc72329a332e7eb1/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "e459acceac81e5fe67c07d9cfc72329a332e7eb1",
      "sha256": "e4f44b9c6924a283f1d1d36057a89f1a04404bf1561fc2c0b64cf98180e72915",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.015625,
        "bos_token_id": 100283,
        "dtype": "bfloat16",
        "embedding_multiplier": 1.0,
        "eos_token_id": 100257,
        "hidden_act": "silu",
        "hidden_size": 2560,
        "initializer_range": 0.1,
        "intermediate_size": 8192,
        "logits_scaling": 1.0,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 40,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 100257,
        "residual_multiplier": 1.0,
        "rms_norm_eps": 1e-05,
        "rope_parameters": {
          "rope_theta": 10000000,
          "rope_type": "default"
        },
        "rope_scaling": null,
        "rope_theta": 10000000,
        "tie_word_embeddings": false,
        "transformers_version": "4.57.1",
        "use_cache": true,
        "vocab_size": 100352,
        "torch_dtype": "bfloat16"
      }
    },
    {
      "id": "ibm-granite/granite-4.2-8b",
      "catalogId": "ibm-granite--granite-4.2-8b",
      "checkedAt": "2026-09-28T06:57:51+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/ibm-granite/granite-4.2-8b/blob/f8de16cdcdbc6c779ca517604e050d82cc119e44/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "f8de16cdcdbc6c779ca517604e050d82cc119e44",
      "sha256": "85611f4e34633d4e148e6a5f64bc2d3a23ebbc2b014bc87fbda764eecf261cd9",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GraniteForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_multiplier": 0.0078125,
        "bos_token_id": 100283,
        "dtype": "bfloat16",
        "embedding_multiplier": 1.0,
        "eos_token_id": 100257,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.1,
        "intermediate_size": 12800,
        "logits_scaling": 1.0,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "granite",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "pad_token_id": 100257,
        "residual_multiplier": 1.0,
        "rms_norm_eps": 1e-05,
        "rope_parameters": {
          "rope_theta": 10000000,
          "rope_type": "default"
        },
        "rope_scaling": null,
        "rope_theta": 10000000,
        "tie_word_embeddings": false,
        "transformers_version": "4.57.1",
        "use_cache": true,
        "vocab_size": 100352,
        "torch_dtype": "bfloat16"
      }
    },
    {
      "id": "meta-llama/Llama-3.1-405B",
      "catalogId": "meta-llama--llama-3.1-405b",
      "checkedAt": "2026-09-28T06:57:51+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Llama-3.1-405B",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "128K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "b906e4dc842aa489c962f9db26554dcfdde901fe",
      "sha256": "97afd6d3762a214519551d0f3b984084c9278523ebdc50f2099d19ee7c39a63c"
    },
    {
      "id": "meta-llama/Llama-3.1-405B-Instruct",
      "catalogId": "meta-llama--llama-3.1-405b-instruct",
      "checkedAt": "2026-09-28T06:57:51+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "128K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "be673f326cab4cd22ccfef76109faf68e41aa5f1",
      "sha256": "b2fbad842b005e2d4b08e28c2447e3d8a3ffacc10601edf10faef2c63b8e785e"
    },
    {
      "id": "meta-llama/Llama-3.1-70B",
      "catalogId": "meta-llama--llama-3.1-70b",
      "checkedAt": "2026-09-28T06:57:51+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Llama-3.1-70B",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "128K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "349b2ddb53ce8f2849a6c168a81980ab25258dac",
      "sha256": "93b7c75933aa9151d60570095613003016c16e7feb95cd400f541482cf2b310e"
    },
    {
      "id": "meta-llama/Llama-3.1-70B-Instruct",
      "catalogId": "meta-llama--llama-3.1-70b-instruct",
      "checkedAt": "2026-09-28T06:57:51+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "128K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "1605565b47bb9346c5515c34102e054115b4f98b",
      "sha256": "8acb47f5abe68188938f06b34de15c2317775fac460f417271395c3f21316ed8"
    },
    {
      "id": "meta-llama/Llama-3.1-8B",
      "catalogId": "meta-llama--llama-3.1-8b",
      "checkedAt": "2026-09-28T06:57:51+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Llama-3.1-8B",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "128K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b",
      "sha256": "e87bef4c0b6cac3061f35a8285a5b84e731edfd1b9064e941fec951f0bc8e9d0"
    },
    {
      "id": "meta-llama/Llama-3.1-8B-Instruct",
      "catalogId": "meta-llama--llama-3.1-8b-instruct",
      "checkedAt": "2026-09-28T06:57:51+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "128K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "0e9e39f249a16976918f6564b8830bc894c89659",
      "sha256": "1c0506fe0aafc495e38b695a8b7b8348ca47af430eb1e2126127cf93ab749ed4"
    },
    {
      "id": "meta-llama/Llama-3.2-1B",
      "catalogId": "meta-llama--llama-3.2-1b",
      "checkedAt": "2026-09-28T06:57:52+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Llama-3.2-1B",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "128K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "4e20de362430cd3b72f300e6b0f18e50e7166e08",
      "sha256": "5cec9cb4566b358ca83ea12e4b33905731dcb5611674f4a80d74bb3f69dc47bf"
    },
    {
      "id": "meta-llama/Llama-3.2-1B-Instruct",
      "catalogId": "meta-llama--llama-3.2-1b-instruct",
      "checkedAt": "2026-09-28T06:57:52+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "128K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "9213176726f574b556790deb65791e0c5aa438b6",
      "sha256": "ebbdcb8b94ceeb974485c86d7e217696573a3b66cf32ea73039d964ce70fbc73"
    },
    {
      "id": "meta-llama/Llama-3.2-3B",
      "catalogId": "meta-llama--llama-3.2-3b",
      "checkedAt": "2026-09-28T06:57:52+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Llama-3.2-3B",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "128K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "13afe5124825b4f3751f836b40dafda64c1ed062",
      "sha256": "23816117f5f9bf1951d956c722b66d4b6852e6ab19fa1761efc677bc82d4f1d4"
    },
    {
      "id": "meta-llama/Llama-3.2-3B-Instruct",
      "catalogId": "meta-llama--llama-3.2-3b-instruct",
      "checkedAt": "2026-09-28T06:57:52+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "128K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "0cb88a4f764b7a12671c53f0838cd831a0843b95",
      "sha256": "b9d58d99746a6c6a9adc40f4c019a8153f9e229a6a8d876cfcf059504ed4c99b"
    },
    {
      "id": "meta-llama/Llama-3.3-70B-Instruct",
      "catalogId": "meta-llama--llama-3.3-70b-instruct",
      "checkedAt": "2026-09-28T06:57:52+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 131072,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "128K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "6f6073b423013f6a7d4d9f39144961bfbfbc386b",
      "sha256": "bb198b216234fe44a50a9ab712310c8ab619cfacb19957a93f098dd3af9aa2f3"
    },
    {
      "id": "meta-llama/Meta-Llama-3-70B",
      "catalogId": "meta-llama--meta-llama-3-70b",
      "checkedAt": "2026-09-28T06:57:52+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Meta-Llama-3-70B",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "8K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "c82494877ce7f6d7d317c56ec081328e382c72fe",
      "sha256": "512f6df980f2a50994bf1d2becbb5accd70373a293470cf95cbe15184f7e4567"
    },
    {
      "id": "meta-llama/Meta-Llama-3-70B-Instruct",
      "catalogId": "meta-llama--meta-llama-3-70b-instruct",
      "checkedAt": "2026-09-28T06:57:53+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "8K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "50fd307e57011801c7833c87efa1984ddf2db42f",
      "sha256": "5b6349534ac013b95d3dbea9aa2a34af6b976712c84662b85881fc7a20b2b7fd"
    },
    {
      "id": "meta-llama/Meta-Llama-3-8B",
      "catalogId": "meta-llama--meta-llama-3-8b",
      "checkedAt": "2026-09-28T06:57:53+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Meta-Llama-3-8B",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "8K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "8cde5ca8380496c9a6cc7ef3a8b46a0372a1d920",
      "sha256": "9a517e4d0284ec0cccd929464fcbd6cf96c03b5997709979c1cd2acbf5300bb6"
    },
    {
      "id": "meta-llama/Meta-Llama-3-8B-Instruct",
      "catalogId": "meta-llama--meta-llama-3-8b-instruct",
      "checkedAt": "2026-09-28T06:57:53+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct",
      "configFetchNote": "HTTPError: HTTP Error 401: Unauthorized",
      "max": 8192,
      "field": "model-card.context-table",
      "evidence": {
        "contextNotation": "8K",
        "normalization": "K = 1024 tokens"
      },
      "revision": "8afb486c1db24fe5011ec46dfbe5b5dccdb575c2",
      "sha256": "4e34f4c4c1bf1d6650df8f69f80c31192886608e8bbcf2d16bceaba785efda2b"
    },
    {
      "id": "microsoft/phi-1",
      "catalogId": "microsoft--phi-1",
      "checkedAt": "2026-09-28T06:57:54+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/phi-1/blob/d4c0adcb065e84e00ca814e35cba3012ea9841ab/config.json",
      "max": 2048,
      "field": "max_position_embeddings",
      "revision": "d4c0adcb065e84e00ca814e35cba3012ea9841ab",
      "sha256": "6a6a640160005481d97389210b2134e24d0ef200c5637c70c364162376448f3b",
      "evidence": {
        "max_position_embeddings": 2048
      },
      "config": {
        "_name_or_path": "microsoft/phi-1",
        "architectures": [
          "PhiForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": null,
        "embd_pdrop": 0.0,
        "eos_token_id": null,
        "hidden_act": "gelu_new",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "layer_norm_eps": 1e-05,
        "max_position_embeddings": 2048,
        "model_type": "phi",
        "num_attention_heads": 32,
        "num_hidden_layers": 24,
        "num_key_value_heads": null,
        "partial_rotary_factor": 0.5,
        "qk_layernorm": false,
        "resid_pdrop": 0.0,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "float32",
        "transformers_version": "4.37.0",
        "use_cache": true,
        "vocab_size": 51200
      }
    },
    {
      "id": "microsoft/phi-1_5",
      "catalogId": "microsoft--phi-1_5",
      "checkedAt": "2026-09-28T06:57:54+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/phi-1_5/blob/77aa61eeac94fbf33d492b9f2744c98b42d5b5eb/config.json",
      "max": 2048,
      "field": "max_position_embeddings",
      "revision": "77aa61eeac94fbf33d492b9f2744c98b42d5b5eb",
      "sha256": "2fe52126434075e8a23aca5bfed8cca8aff7051779e6f11c76de9e9e9923dcef",
      "evidence": {
        "max_position_embeddings": 2048
      },
      "config": {
        "_name_or_path": "microsoft/phi-1_5",
        "architectures": [
          "PhiForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": null,
        "embd_pdrop": 0.0,
        "eos_token_id": null,
        "hidden_act": "gelu_new",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "layer_norm_eps": 1e-05,
        "max_position_embeddings": 2048,
        "model_type": "phi",
        "num_attention_heads": 32,
        "num_hidden_layers": 24,
        "num_key_value_heads": null,
        "partial_rotary_factor": 0.5,
        "qk_layernorm": false,
        "resid_pdrop": 0.0,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "float16",
        "transformers_version": "4.37.0",
        "use_cache": true,
        "vocab_size": 51200
      }
    },
    {
      "id": "microsoft/phi-2",
      "catalogId": "microsoft--phi-2",
      "checkedAt": "2026-09-28T06:57:54+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/phi-2/blob/810d367871c1d460086d9f82db8696f2e0a0fcd0/config.json",
      "max": 2048,
      "field": "max_position_embeddings",
      "revision": "810d367871c1d460086d9f82db8696f2e0a0fcd0",
      "sha256": "fbd955b298fdbd35fb81b3350a0d68d12616da7b7e9d81397ef632038ccc1111",
      "evidence": {
        "max_position_embeddings": 2048
      },
      "config": {
        "_name_or_path": "microsoft/phi-2",
        "architectures": [
          "PhiForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 50256,
        "embd_pdrop": 0.0,
        "eos_token_id": 50256,
        "hidden_act": "gelu_new",
        "hidden_size": 2560,
        "initializer_range": 0.02,
        "intermediate_size": 10240,
        "layer_norm_eps": 1e-05,
        "max_position_embeddings": 2048,
        "model_type": "phi",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 32,
        "partial_rotary_factor": 0.4,
        "qk_layernorm": false,
        "resid_pdrop": 0.1,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "float16",
        "transformers_version": "4.37.0",
        "use_cache": true,
        "vocab_size": 51200
      }
    },
    {
      "id": "microsoft/Phi-3-medium-128k-instruct",
      "catalogId": "microsoft--phi-3-medium-128k-instruct",
      "checkedAt": "2026-09-28T06:57:54+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/blob/a088b37c71d441ab6d862bb3fcfe6165b3014702/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "a088b37c71d441ab6d862bb3fcfe6165b3014702",
      "sha256": "8e891959ffa989ab500e0ec2eb60e7af4e3c89afe8d58642d8f0698d2ebe90d2",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "_name_or_path": "Phi-3-medium-128k-instruct",
        "architectures": [
          "Phi3ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_phi3.Phi3Config",
          "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
        },
        "bos_token_id": 1,
        "embd_pdrop": 0.0,
        "eos_token_id": 32000,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 17920,
        "max_position_embeddings": 131072,
        "model_type": "phi3",
        "num_attention_heads": 40,
        "num_hidden_layers": 40,
        "num_key_value_heads": 10,
        "original_max_position_embeddings": 4096,
        "pad_token_id": null,
        "resid_pdrop": 0.0,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "long_factor": [
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.25,
            1.25,
            1.5,
            2.0,
            2.75,
            5.75,
            5.75,
            6.5,
            9.25,
            11.0,
            13.25,
            19.25,
            19.75,
            19.75,
            21.25,
            21.5,
            26.5,
            30.0,
            33.75,
            35.25,
            38.5,
            42.0,
            42.25,
            46.0,
            47.0,
            50.0,
            50.5,
            51.0,
            52.0,
            52.75,
            53.75,
            54.75,
            57.0,
            57.25,
            58.5,
            59.25,
            59.5,
            62.0,
            62.5,
            62.75,
            63.25,
            63.25,
            63.25,
            63.75,
            64.0,
            64.0,
            64.25,
            64.5,
            64.5,
            65.0,
            65.0
          ],
          "short_factor": [
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.01,
            1.02,
            1.02,
            1.04,
            1.04,
            1.07,
            1.07,
            1.1,
            1.3000000000000003,
            1.3000000000000003,
            1.5000000000000004,
            1.5700000000000005,
            1.9000000000000008,
            2.3100000000000014,
            2.759999999999992,
            3.3899999999999784,
            3.9399999999999666,
            4.009999999999965,
            4.289999999999959,
            4.349999999999958,
            5.349999999999937,
            6.659999999999909,
            7.029999999999901,
            7.51999999999989,
            8.00999999999988,
            8.249999999999876,
            8.279999999999875,
            9.629999999999846,
            9.89999999999984,
            10.589999999999826,
            11.049999999999816,
            11.7899999999998,
            12.189999999999792,
            12.889999999999777,
            13.129999999999772,
            13.16999999999977,
            13.20999999999977,
            13.479999999999764,
            13.539999999999763,
            13.779999999999758,
            13.929999999999755,
            14.429999999999744,
            14.759999999999737,
            15.149999999999729,
            15.419999999999723,
            15.53999999999972,
            15.659999999999718,
            15.749999999999716,
            15.759999999999716,
            15.799999999999715,
            16.05999999999971,
            16.079999999999714,
            16.11999999999972,
            16.11999999999972,
            16.18999999999973,
            16.31999999999975,
            16.539999999999786,
            16.799999999999827
          ],
          "type": "su"
        },
        "rope_theta": 10000.0,
        "sliding_window": 131072,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.39.3",
        "use_cache": true,
        "attention_bias": false,
        "vocab_size": 32064
      }
    },
    {
      "id": "microsoft/Phi-3-medium-4k-instruct",
      "catalogId": "microsoft--phi-3-medium-4k-instruct",
      "checkedAt": "2026-09-28T06:57:54+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/blob/48d87cd5e0523b430d77e93becd3655cd6897230/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "48d87cd5e0523b430d77e93becd3655cd6897230",
      "sha256": "0e2dee0d6396679ed3e51bece60f063d506ea791fdb445a0d65a7f3e2d9aa6e7",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "_name_or_path": "Phi-3-medium-4k-instruct",
        "architectures": [
          "Phi3ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_phi3.Phi3Config",
          "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
        },
        "bos_token_id": 1,
        "embd_pdrop": 0.0,
        "eos_token_id": 32000,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 17920,
        "max_position_embeddings": 4096,
        "model_type": "phi3",
        "num_attention_heads": 40,
        "num_hidden_layers": 40,
        "num_key_value_heads": 10,
        "original_max_position_embeddings": 4096,
        "pad_token_id": 32000,
        "resid_pdrop": 0.0,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "sliding_window": 2047,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.39.3",
        "use_cache": true,
        "attention_bias": false,
        "vocab_size": 32064
      }
    },
    {
      "id": "microsoft/Phi-3-mini-128k-instruct",
      "catalogId": "microsoft--phi-3-mini-128k-instruct",
      "checkedAt": "2026-09-28T06:57:54+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/blob/f3c06aed622e14ca0abf5115094e4fc9a9948f36/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "f3c06aed622e14ca0abf5115094e4fc9a9948f36",
      "sha256": "af70441b867458d18788c564ea69894adddaa4de47ab6534391604fc4893f03b",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "_name_or_path": "Phi-3-mini-128k-instruct",
        "architectures": [
          "Phi3ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_phi3.Phi3Config",
          "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
        },
        "bos_token_id": 1,
        "embd_pdrop": 0.0,
        "eos_token_id": 32000,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "max_position_embeddings": 131072,
        "model_type": "phi3",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 32,
        "original_max_position_embeddings": 4096,
        "pad_token_id": 32000,
        "resid_pdrop": 0.0,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "long_factor": [
            1.0700000524520874,
            1.1200000047683716,
            1.149999976158142,
            1.4199999570846558,
            1.5699999332427979,
            1.7999999523162842,
            2.129999876022339,
            2.129999876022339,
            3.009999990463257,
            5.910000324249268,
            6.950000286102295,
            9.070000648498535,
            9.930000305175781,
            10.710000038146973,
            11.130000114440918,
            14.609999656677246,
            15.409998893737793,
            19.809999465942383,
            37.279998779296875,
            38.279998779296875,
            38.599998474121094,
            40.12000274658203,
            46.20000457763672,
            50.940006256103516,
            53.66000747680664,
            54.9373893737793,
            56.89738845825195,
            57.28738784790039,
            59.98738479614258,
            60.86738586425781,
            60.887386322021484,
            61.71739196777344,
            62.91739273071289,
            62.957393646240234,
            63.41739273071289,
            63.8173942565918,
            63.83739471435547,
            63.897396087646484,
            63.93739700317383,
            64.06739807128906,
            64.11434936523438,
            64.12435150146484,
            64.15435028076172,
            64.19435119628906,
            64.24435424804688,
            64.57435607910156,
            64.69000244140625,
            64.76000213623047
          ],
          "short_factor": [
            1.1,
            1.1,
            1.1,
            1.3000000000000003,
            1.3500000000000003,
            1.3500000000000003,
            1.4000000000000004,
            1.5500000000000005,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.000000000000001,
            2.0500000000000007,
            2.0500000000000007,
            2.0500000000000007,
            2.0500000000000007,
            2.0500000000000007,
            2.0500000000000007,
            2.1000000000000005,
            2.1000000000000005,
            2.1500000000000004,
            2.25,
            2.25,
            2.25,
            2.25,
            2.25,
            2.3999999999999995,
            2.4499999999999993,
            2.499999999999999,
            2.6999999999999984,
            2.6999999999999984,
            2.7499999999999982,
            2.799999999999998,
            2.8999999999999977,
            3.049999999999997
          ],
          "type": "longrope"
        },
        "rope_theta": 10000.0,
        "sliding_window": 262144,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.2",
        "use_cache": true,
        "attention_bias": false,
        "vocab_size": 32064
      }
    },
    {
      "id": "microsoft/Phi-3-mini-4k-instruct",
      "catalogId": "microsoft--phi-3-mini-4k-instruct",
      "checkedAt": "2026-09-28T06:57:54+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/f39ac1d28e925b323eae81227eaba4464caced4e/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "f39ac1d28e925b323eae81227eaba4464caced4e",
      "sha256": "072d4df63228ef806a6b2b2f02a93f1d048ebd31584d0f61d1180aef36e5bcea",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "_name_or_path": "Phi-3-mini-4k-instruct",
        "architectures": [
          "Phi3ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_phi3.Phi3Config",
          "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
        },
        "bos_token_id": 1,
        "embd_pdrop": 0.0,
        "eos_token_id": 32000,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "max_position_embeddings": 4096,
        "model_type": "phi3",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 32,
        "original_max_position_embeddings": 4096,
        "pad_token_id": 32000,
        "resid_pdrop": 0.0,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "sliding_window": 2047,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.2",
        "use_cache": true,
        "attention_bias": false,
        "vocab_size": 32064
      }
    },
    {
      "id": "microsoft/Phi-3.5-mini-instruct",
      "catalogId": "microsoft--phi-3.5-mini-instruct",
      "checkedAt": "2026-09-28T06:57:54+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/Phi-3.5-mini-instruct/blob/2fe192450127e6a83f7441aef6e3ca586c338b77/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "2fe192450127e6a83f7441aef6e3ca586c338b77",
      "sha256": "224de4f6a15b9d2a89695ec04b7f7ab2dd93a008a506979925e5a88cb5804974",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "_name_or_path": "Phi-3.5-mini-instruct",
        "architectures": [
          "Phi3ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_phi3.Phi3Config",
          "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
        },
        "bos_token_id": 1,
        "embd_pdrop": 0.0,
        "eos_token_id": 32000,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "max_position_embeddings": 131072,
        "model_type": "phi3",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 32,
        "original_max_position_embeddings": 4096,
        "pad_token_id": 32000,
        "resid_pdrop": 0.0,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "long_factor": [
            1.0800000429153442,
            1.1100000143051147,
            1.1399999856948853,
            1.340000033378601,
            1.5899999141693115,
            1.600000023841858,
            1.6200000047683716,
            2.620000123977661,
            3.2300000190734863,
            3.2300000190734863,
            4.789999961853027,
            7.400000095367432,
            7.700000286102295,
            9.09000015258789,
            12.199999809265137,
            17.670000076293945,
            24.46000099182129,
            28.57000160217285,
            30.420001983642578,
            30.840002059936523,
            32.590003967285156,
            32.93000411987305,
            42.320003509521484,
            44.96000289916992,
            50.340003967285156,
            50.45000457763672,
            57.55000305175781,
            57.93000411987305,
            58.21000289916992,
            60.1400032043457,
            62.61000442504883,
            62.62000274658203,
            62.71000289916992,
            63.1400032043457,
            63.1400032043457,
            63.77000427246094,
            63.93000411987305,
            63.96000289916992,
            63.970001220703125,
            64.02999877929688,
            64.06999969482422,
            64.08000183105469,
            64.12000274658203,
            64.41000366210938,
            64.4800033569336,
            64.51000213623047,
            64.52999877929688,
            64.83999633789062
          ],
          "short_factor": [
            1.0,
            1.0199999809265137,
            1.0299999713897705,
            1.0299999713897705,
            1.0499999523162842,
            1.0499999523162842,
            1.0499999523162842,
            1.0499999523162842,
            1.0499999523162842,
            1.0699999332427979,
            1.0999999046325684,
            1.1099998950958252,
            1.1599998474121094,
            1.1599998474121094,
            1.1699998378753662,
            1.2899998426437378,
            1.339999794960022,
            1.679999828338623,
            1.7899998426437378,
            1.8199998140335083,
            1.8499997854232788,
            1.8799997568130493,
            1.9099997282028198,
            1.9399996995925903,
            1.9899996519088745,
            2.0199997425079346,
            2.0199997425079346,
            2.0199997425079346,
            2.0199997425079346,
            2.0199997425079346,
            2.0199997425079346,
            2.0299997329711914,
            2.0299997329711914,
            2.0299997329711914,
            2.0299997329711914,
            2.0299997329711914,
            2.0299997329711914,
            2.0299997329711914,
            2.0299997329711914,
            2.0299997329711914,
            2.0799996852874756,
            2.0899996757507324,
            2.189999580383301,
            2.2199995517730713,
            2.5899994373321533,
            2.729999542236328,
            2.749999523162842,
            2.8399994373321533
          ],
          "type": "longrope"
        },
        "rope_theta": 10000.0,
        "sliding_window": 262144,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.3",
        "use_cache": true,
        "attention_bias": false,
        "vocab_size": 32064
      }
    },
    {
      "id": "microsoft/Phi-3.5-MoE-instruct",
      "catalogId": "microsoft--phi-3.5-moe-instruct",
      "checkedAt": "2026-09-28T06:57:54+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/Phi-3.5-MoE-instruct/blob/43688451b462a3351d8580625ebe1931adb3986d/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "43688451b462a3351d8580625ebe1931adb3986d",
      "sha256": "0b7d26ba176054d43f2b47012ec7cb01868ae7078693757f940e90c13e5bae15",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "_name_or_path": "Phi-3.5-MoE-instruct",
        "architectures": [
          "PhiMoEForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_phimoe.PhiMoEConfig",
          "AutoModelForCausalLM": "modeling_phimoe.PhiMoEForCausalLM"
        },
        "bos_token_id": 1,
        "eos_token_id": 32000,
        "hidden_act": "silu",
        "hidden_dropout": 0.0,
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "input_jitter_noise": 0.01,
        "intermediate_size": 6400,
        "lm_head_bias": true,
        "max_position_embeddings": 131072,
        "model_type": "phimoe",
        "num_attention_heads": 32,
        "num_experts_per_tok": 2,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "num_local_experts": 16,
        "original_max_position_embeddings": 4096,
        "output_router_logits": false,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "long_factor": [
            1.0199999809265137,
            1.0299999713897705,
            1.0399999618530273,
            1.0499999523162842,
            1.0499999523162842,
            1.0499999523162842,
            1.059999942779541,
            1.059999942779541,
            1.059999942779541,
            1.059999942779541,
            1.059999942779541,
            1.059999942779541,
            1.0999999046325684,
            1.1799999475479126,
            1.1799999475479126,
            1.3700000047683716,
            1.4899998903274536,
            2.109999895095825,
            2.8899998664855957,
            3.9499998092651367,
            4.299999713897705,
            6.429999828338623,
            8.09000015258789,
            10.690000534057617,
            12.050000190734863,
            18.229999542236328,
            18.84000015258789,
            19.899999618530273,
            21.420000076293945,
            26.200000762939453,
            34.28000259399414,
            34.590003967285156,
            38.730003356933594,
            40.22000503540039,
            42.54000473022461,
            44.000003814697266,
            47.590003967285156,
            54.750003814697266,
            56.19000244140625,
            57.44000244140625,
            57.4900016784668,
            61.20000076293945,
            61.540000915527344,
            61.75,
            61.779998779296875,
            62.06999969482422,
            63.11000061035156,
            63.43000030517578,
            63.560001373291016,
            63.71000289916992,
            63.92000198364258,
            63.94000244140625,
            63.94000244140625,
            63.96000289916992,
            63.980003356933594,
            64.0300064086914,
            64.0300064086914,
            64.0300064086914,
            64.04000854492188,
            64.10000610351562,
            64.19000244140625,
            64.20999908447266,
            64.75,
            64.95999908447266
          ],
          "long_mscale": 1.243163121016122,
          "original_max_position_embeddings": 4096,
          "short_factor": [
            1.0,
            1.0399999618530273,
            1.0399999618530273,
            1.0399999618530273,
            1.0499999523162842,
            1.0499999523162842,
            1.0499999523162842,
            1.0499999523162842,
            1.0499999523162842,
            1.0499999523162842,
            1.0499999523162842,
            1.0499999523162842,
            1.0499999523162842,
            1.0499999523162842,
            1.059999942779541,
            1.059999942779541,
            1.0699999332427979,
            1.0699999332427979,
            1.0699999332427979,
            1.0699999332427979,
            1.1399999856948853,
            1.159999966621399,
            1.159999966621399,
            1.159999966621399,
            1.159999966621399,
            1.1799999475479126,
            1.1999999284744263,
            1.3199999332427979,
            1.3399999141693115,
            1.3499999046325684,
            1.3999998569488525,
            1.4799998998641968,
            1.4999998807907104,
            1.589999794960022,
            1.6499998569488525,
            1.71999990940094,
            1.8999998569488525,
            1.9099998474121094,
            1.9099998474121094,
            1.9899998903274536,
            1.9999998807907104,
            1.9999998807907104,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.009999990463257,
            2.0999999046325684,
            2.319999933242798,
            2.419999837875366,
            2.5899999141693115,
            2.7899999618530273
          ],
          "short_mscale": 1.243163121016122,
          "type": "longrope"
        },
        "rope_theta": 10000.0,
        "router_aux_loss_coef": 0.0,
        "router_jitter_noise": 0.01,
        "sliding_window": 131072,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.3",
        "use_cache": true,
        "vocab_size": 32064
      }
    },
    {
      "id": "microsoft/phi-4",
      "catalogId": "microsoft--phi-4",
      "checkedAt": "2026-09-28T06:57:54+00:00",
      "previousMax": 16384,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/phi-4/blob/2db69c1c3e91a05d2c64a3185acfbaf36f744e25/config.json",
      "max": 16384,
      "field": "max_position_embeddings",
      "revision": "2db69c1c3e91a05d2c64a3185acfbaf36f744e25",
      "sha256": "07eedad2c48798b6e3728e4a1b75e0e092019a375ba725a40e40c78d13664045",
      "evidence": {
        "max_position_embeddings": 16384
      },
      "config": {
        "_name_or_path": "microsoft/phi-4",
        "architectures": [
          "Phi3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 100257,
        "embd_pdrop": 0.0,
        "eos_token_id": 100265,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 17920,
        "max_position_embeddings": 16384,
        "model_type": "phi3",
        "num_attention_heads": 40,
        "num_hidden_layers": 40,
        "num_key_value_heads": 10,
        "original_max_position_embeddings": 16384,
        "pad_token_id": 100349,
        "resid_pdrop": 0.0,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 250000,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.47.0",
        "use_cache": true,
        "vocab_size": 100352
      }
    },
    {
      "id": "microsoft/Phi-4-mini-instruct",
      "catalogId": "microsoft--phi-4-mini-instruct",
      "checkedAt": "2026-09-28T06:57:54+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/Phi-4-mini-instruct/blob/cfbefacb99257ffa30c83adab238a50856ac3083/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "cfbefacb99257ffa30c83adab238a50856ac3083",
      "sha256": "ac65d86061d3d0d704ee2511fd0eb8713ef19eb6eedba17c3080a4165d5b933b",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "_name_or_path": "Phi-4-mini-instruct",
        "architectures": [
          "Phi3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_phi3.Phi3Config",
          "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
          "AutoTokenizer": "Xenova/gpt-4o"
        },
        "bos_token_id": 199999,
        "embd_pdrop": 0.0,
        "eos_token_id": 199999,
        "full_attn_mod": 1,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "interpolate_factor": 1,
        "lm_head_bias": false,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "phi3",
        "num_attention_heads": 24,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "original_max_position_embeddings": 4096,
        "pad_token_id": 199999,
        "partial_rotary_factor": 0.75,
        "resid_pdrop": 0.0,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "long_factor": [
            1,
            1.118320672,
            1.250641126,
            1.398617824,
            1.564103225,
            1.74916897,
            1.956131817,
            2.187582649,
            2.446418898,
            2.735880826,
            3.059592084,
            3.421605075,
            3.826451687,
            4.279200023,
            4.785517845,
            5.351743533,
            5.984965424,
            6.693110555,
            7.485043894,
            8.370679318,
            9.36110372,
            10.4687158,
            11.70738129,
            13.09260651,
            14.64173252,
            16.37415215,
            18.31155283,
            20.47818807,
            22.90118105,
            25.61086418,
            28.64115884,
            32.03,
            32.1,
            32.13,
            32.23,
            32.6,
            32.61,
            32.64,
            32.66,
            32.7,
            32.71,
            32.93,
            32.97,
            33.28,
            33.49,
            33.5,
            44.16,
            47.77
          ],
          "short_factor": [
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0,
            1.0
          ],
          "type": "longrope"
        },
        "rope_theta": 10000.0,
        "sliding_window": 262144,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.45.0",
        "use_cache": true,
        "vocab_size": 200064
      }
    },
    {
      "id": "microsoft/Phi-4-mini-reasoning",
      "catalogId": "microsoft--phi-4-mini-reasoning",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/Phi-4-mini-reasoning/blob/0e3b1e2d02ee478a3743abe3f629e9c0cb722e0a/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "0e3b1e2d02ee478a3743abe3f629e9c0cb722e0a",
      "sha256": "2283ba68d420b7fddf4be894361142dfa34636c0a81e3af819cc1e660f128f6c",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "Phi3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 199999,
        "embd_pdrop": 0.0,
        "eos_token_id": 199999,
        "full_attn_mod": 1,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "interpolate_factor": 1,
        "lm_head_bias": false,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "phi3",
        "num_attention_heads": 24,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "original_max_position_embeddings": 4096,
        "pad_token_id": 199999,
        "partial_rotary_factor": 0.75,
        "resid_pdrop": 0.0,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "long_factor": [
            1,
            1.118320672,
            1.250641126,
            1.398617824,
            1.564103225,
            1.74916897,
            1.956131817,
            2.187582649,
            2.446418898,
            2.735880826,
            3.059592084,
            3.421605075,
            3.826451687,
            4.279200023,
            4.785517845,
            5.351743533,
            5.984965424,
            6.693110555,
            7.485043894,
            8.370679318,
            9.36110372,
            10.4687158,
            11.70738129,
            13.09260651,
            14.64173252,
            16.37415215,
            18.31155283,
            20.47818807,
            22.90118105,
            25.61086418,
            28.64115884,
            32.03,
            32.1,
            32.13,
            32.23,
            32.6,
            32.61,
            32.64,
            32.66,
            32.7,
            32.71,
            32.93,
            32.97,
            33.28,
            33.49,
            33.5,
            44.16,
            47.77
          ],
          "short_factor": [
            1,
            1.118320672,
            1.250641126,
            1.398617824,
            1.564103225,
            1.74916897,
            1.956131817,
            2.187582649,
            2.446418898,
            2.735880826,
            3.059592084,
            3.421605075,
            3.826451687,
            4.279200023,
            4.785517845,
            5.351743533,
            5.984965424,
            6.693110555,
            7.485043894,
            8.370679318,
            9.36110372,
            10.4687158,
            11.70738129,
            13.09260651,
            14.64173252,
            16.37415215,
            18.31155283,
            20.47818807,
            22.90118105,
            25.61086418,
            28.64115884,
            32.03,
            32.1,
            32.13,
            32.23,
            32.6,
            32.61,
            32.64,
            32.66,
            32.7,
            32.71,
            32.93,
            32.97,
            33.28,
            33.49,
            33.5,
            44.16,
            47.77
          ],
          "type": "longrope"
        },
        "rope_theta": 10000.0,
        "sliding_window": 262144,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.50.0",
        "use_cache": true,
        "vocab_size": 200064
      }
    },
    {
      "id": "microsoft/Phi-4-reasoning",
      "catalogId": "microsoft--phi-4-reasoning",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/Phi-4-reasoning/blob/1de18ec97600877ce63dbf60c73b998da99f0195/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "1de18ec97600877ce63dbf60c73b998da99f0195",
      "sha256": "0a13d8a96ac97a77871e10739669fd75cb1d7e2e403d5cd6ee0819233a30eff8",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Phi3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 100257,
        "embd_pdrop": 0.0,
        "eos_token_id": 100265,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 17920,
        "max_position_embeddings": 32768,
        "model_type": "phi3",
        "num_attention_heads": 40,
        "num_hidden_layers": 40,
        "num_key_value_heads": 10,
        "original_max_position_embeddings": 32768,
        "pad_token_id": 100349,
        "partial_rotary_factor": 1.0,
        "resid_pdrop": 0.0,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 500000,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.1",
        "use_cache": true,
        "vocab_size": 100352
      }
    },
    {
      "id": "microsoft/Phi-4-reasoning-plus",
      "catalogId": "microsoft--phi-4-reasoning-plus",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/Phi-4-reasoning-plus/blob/69baf8528e1bcf05f475034d9e5dd32875ed125f/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "69baf8528e1bcf05f475034d9e5dd32875ed125f",
      "sha256": "0a13d8a96ac97a77871e10739669fd75cb1d7e2e403d5cd6ee0819233a30eff8",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Phi3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 100257,
        "embd_pdrop": 0.0,
        "eos_token_id": 100265,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 17920,
        "max_position_embeddings": 32768,
        "model_type": "phi3",
        "num_attention_heads": 40,
        "num_hidden_layers": 40,
        "num_key_value_heads": 10,
        "original_max_position_embeddings": 32768,
        "pad_token_id": 100349,
        "partial_rotary_factor": 1.0,
        "resid_pdrop": 0.0,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 500000,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.1",
        "use_cache": true,
        "vocab_size": 100352
      }
    },
    {
      "id": "microsoft/Phi-mini-MoE-instruct",
      "catalogId": "microsoft--phi-mini-moe-instruct",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/Phi-mini-MoE-instruct/blob/f620b32c0d3e8f7e76f57ccdaa88e0df8bc8bfcd/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "f620b32c0d3e8f7e76f57ccdaa88e0df8bc8bfcd",
      "sha256": "9594149f9fed36a5f74cace363b38423b39be5983c7146930c5569807cd2c90c",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "_name_or_path": "Phi-mini-MoE",
        "architectures": [
          "PhiMoEForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_slimmoe.PhiMoEConfig",
          "AutoModelForCausalLM": "modeling_slimmoe.PhiMoEForCausalLM"
        },
        "bos_token_id": 1,
        "eos_token_id": 32000,
        "expert_dropout": 0.0,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_dropout": 0.0,
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "input_jitter_noise": 0.01,
        "intermediate_size": 960,
        "lm_head_bias": true,
        "max_position_embeddings": 4096,
        "model_type": "phimoe",
        "num_attention_heads": 32,
        "num_experts_per_tok": 2,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "num_local_experts": 16,
        "output_router_logits": false,
        "rms_norm_eps": 1e-05,
        "rope_theta": 10000.0,
        "router_aux_loss_coef": 0.0,
        "router_jitter_noise": 0.01,
        "sliding_window": 2047,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.3",
        "use_cache": true,
        "vocab_size": 32064
      }
    },
    {
      "id": "microsoft/Phi-tiny-MoE-instruct",
      "catalogId": "microsoft--phi-tiny-moe-instruct",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/microsoft/Phi-tiny-MoE-instruct/blob/2fe50e88d0e2a5a132563815686ea0dcc8e252b5/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "2fe50e88d0e2a5a132563815686ea0dcc8e252b5",
      "sha256": "cdc9b948bf96ecbd2facb5540bc113621a74baf67e8e02fd50121fcc6db32354",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "_name_or_path": "Phi-tiny-MoE",
        "architectures": [
          "PhiMoEForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_slimmoe.PhiMoEConfig",
          "AutoModelForCausalLM": "modeling_slimmoe.PhiMoEForCausalLM"
        },
        "bos_token_id": 1,
        "eos_token_id": 32000,
        "expert_dropout": 0.0,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_dropout": 0.0,
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "input_jitter_noise": 0.01,
        "intermediate_size": 448,
        "lm_head_bias": true,
        "max_position_embeddings": 4096,
        "model_type": "phimoe",
        "num_attention_heads": 16,
        "num_experts_per_tok": 2,
        "num_hidden_layers": 32,
        "num_key_value_heads": 4,
        "num_local_experts": 16,
        "output_router_logits": false,
        "rms_norm_eps": 1e-05,
        "rope_theta": 10000.0,
        "router_aux_loss_coef": 0.0,
        "router_jitter_noise": 0.01,
        "sliding_window": 2047,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.3",
        "use_cache": true,
        "vocab_size": 32064
      }
    },
    {
      "id": "mistralai/Devstral-Small-2505",
      "catalogId": "mistralai--devstral-small-2505",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Devstral-Small-2505/blob/c2a9d81a2989af566682b4cecc828c84556076c5/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "c2a9d81a2989af566682b4cecc828c84556076c5",
      "sha256": "1cc8c0ff7a35a6dd6a3995eea5b6d480691636841982f1d19d303239da6c86e3",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "MistralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 32768,
        "max_position_embeddings": 131072,
        "model_type": "mistral",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000000.0,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.3",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "mistralai/Magistral-Small-2506",
      "catalogId": "mistralai--magistral-small-2506",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 40960,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Magistral-Small-2506/blob/ad2fce5b4113139e1877dcadfd826c9262ad8e8c/config.json",
      "max": 40960,
      "field": "max_position_embeddings",
      "revision": "ad2fce5b4113139e1877dcadfd826c9262ad8e8c",
      "sha256": "92fee9e7d530377df3510b8ec683cccbb8c93d59ecdb1cd7fb6012d924214126",
      "evidence": {
        "max_position_embeddings": 40960
      },
      "config": {
        "architectures": [
          "MistralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 32768,
        "max_position_embeddings": 40960,
        "model_type": "mistral",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000000.0,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.52.4",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "mistralai/Ministral-8B-Instruct-2410",
      "catalogId": "mistralai--ministral-8b-instruct-2410",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Ministral-8B-Instruct-2410/blob/2f494a194c5b980dfb9772cb92d26cbb671fce5a/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "2f494a194c5b980dfb9772cb92d26cbb671fce5a",
      "sha256": "c675c1d724fdf951ba97b7241da3b1dab23371ab6af069f20c4001eaa0ce1dd6",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "MistralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 12288,
        "layer_types": [
          "full_attention",
          "sliding_attention",
          "sliding_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "sliding_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "sliding_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "sliding_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "sliding_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "sliding_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "sliding_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "sliding_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "sliding_attention",
          "sliding_attention"
        ],
        "max_position_embeddings": 32768,
        "model_type": "mistral",
        "num_attention_heads": 32,
        "num_hidden_layers": 36,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 100000000.0,
        "sliding_window": 32768,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.0.dev0",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "mistralai/Mistral-7B-Instruct-v0.1",
      "catalogId": "mistralai--mistral-7b-instruct-v0.1",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1/blob/ec5deb64f2c6e6fa90c1abf74a91d5c93a9669ca/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "ec5deb64f2c6e6fa90c1abf74a91d5c93a9669ca",
      "sha256": "cf25cdf4719f181d1d1d371973285d9afe9afde0d0c6a6fd48de857555ce1e0d",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "MistralForCausalLM"
        ],
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 32768,
        "model_type": "mistral",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 10000.0,
        "sliding_window": 4096,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.34.0.dev0",
        "use_cache": true,
        "vocab_size": 32000
      }
    },
    {
      "id": "mistralai/Mistral-7B-Instruct-v0.2",
      "catalogId": "mistralai--mistral-7b-instruct-v0.2",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2/blob/63a8b081895390a26e140280378bc85ec8bce07a/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "63a8b081895390a26e140280378bc85ec8bce07a",
      "sha256": "2e97da1b1d2b7e7669f0991c186904538c27d4ea56c4fc74e89215e2b2013922",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "MistralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 32768,
        "model_type": "mistral",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000.0,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.36.0",
        "use_cache": true,
        "vocab_size": 32000
      }
    },
    {
      "id": "mistralai/Mistral-7B-Instruct-v0.3",
      "catalogId": "mistralai--mistral-7b-instruct-v0.3",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3/blob/c170c708c41dac9275d15a8fff4eca08d52bab71/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "c170c708c41dac9275d15a8fff4eca08d52bab71",
      "sha256": "affafc6478ec0fd07a32f0ca57aa2fc57743f4d17d6730f86a96ac24d1507f99",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "MistralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 32768,
        "model_type": "mistral",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000.0,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.42.0.dev0",
        "use_cache": true,
        "vocab_size": 32768
      }
    },
    {
      "id": "mistralai/Mistral-7B-v0.1",
      "catalogId": "mistralai--mistral-7b-v0.1",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Mistral-7B-v0.1/blob/27d67f1b5f57dc0953326b2601d68371d40ea8da/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "27d67f1b5f57dc0953326b2601d68371d40ea8da",
      "sha256": "cf25cdf4719f181d1d1d371973285d9afe9afde0d0c6a6fd48de857555ce1e0d",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "MistralForCausalLM"
        ],
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 32768,
        "model_type": "mistral",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 10000.0,
        "sliding_window": 4096,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.34.0.dev0",
        "use_cache": true,
        "vocab_size": 32000
      }
    },
    {
      "id": "mistralai/Mistral-Nemo-Instruct-2407",
      "catalogId": "mistralai--mistral-nemo-instruct-2407",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407/blob/04d8a90549d23fc6bd7f642064003592df51e9b3/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "04d8a90549d23fc6bd7f642064003592df51e9b3",
      "sha256": "8a42669219f4caadedb891be88c34712572573d42b3d02d665d527f92d94ddfe",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "MistralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 131072,
        "model_type": "mistral",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000.0,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.0.dev0",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "mistralai/Mistral-Small-24B-Instruct-2501",
      "catalogId": "mistralai--mistral-small-24b-instruct-2501",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501/blob/9527884be6e5616bdd54de542f9ae13384489724/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "9527884be6e5616bdd54de542f9ae13384489724",
      "sha256": "ff5f8d1747db4e16def20db719d867e74d0b764330249357351b2b44520b8001",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "MistralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 32768,
        "max_position_embeddings": 32768,
        "model_type": "mistral",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 100000000.0,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.49.0.dev0",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "mistralai/Mixtral-8x22B-Instruct-v0.1",
      "catalogId": "mistralai--mixtral-8x22b-instruct-v0.1",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 65536,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1/blob/cc88a6cc19fbd17d9f1c0ee0b0d70a748dce698d/config.json",
      "max": 65536,
      "field": "max_position_embeddings",
      "revision": "cc88a6cc19fbd17d9f1c0ee0b0d70a748dce698d",
      "sha256": "9c4a6138d84029ab666943613e3d5844d2ea8fd6149f44f77188c62e2915e0f5",
      "evidence": {
        "max_position_embeddings": 65536
      },
      "config": {
        "architectures": [
          "MixtralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 6144,
        "initializer_range": 0.02,
        "intermediate_size": 16384,
        "max_position_embeddings": 65536,
        "model_type": "mixtral",
        "num_attention_heads": 48,
        "num_experts_per_tok": 2,
        "num_hidden_layers": 56,
        "num_key_value_heads": 8,
        "num_local_experts": 8,
        "output_router_logits": false,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000.0,
        "router_aux_loss_coef": 0.001,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.38.0",
        "use_cache": true,
        "vocab_size": 32768
      }
    },
    {
      "id": "mistralai/Mixtral-8x22B-v0.1",
      "catalogId": "mistralai--mixtral-8x22b-v0.1",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 65536,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Mixtral-8x22B-v0.1/blob/e1cd34ff1747406fb2277635ed25242803009bc2/config.json",
      "max": 65536,
      "field": "max_position_embeddings",
      "revision": "e1cd34ff1747406fb2277635ed25242803009bc2",
      "sha256": "289373ddfa7e553901931368a57ddf21b0065662cbaf7591e14f486d828e628e",
      "evidence": {
        "max_position_embeddings": 65536
      },
      "config": {
        "architectures": [
          "MixtralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 6144,
        "initializer_range": 0.02,
        "intermediate_size": 16384,
        "max_position_embeddings": 65536,
        "model_type": "mixtral",
        "num_attention_heads": 48,
        "num_experts_per_tok": 2,
        "num_hidden_layers": 56,
        "num_key_value_heads": 8,
        "num_local_experts": 8,
        "output_router_logits": false,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000,
        "router_aux_loss_coef": 0.001,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.38.0",
        "use_cache": true,
        "vocab_size": 32000
      }
    },
    {
      "id": "mistralai/Mixtral-8x7B-Instruct-v0.1",
      "catalogId": "mistralai--mixtral-8x7b-instruct-v0.1",
      "checkedAt": "2026-09-28T06:57:55+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1/blob/eba92302a2861cdc0098cc54bc9f17cb2c47eb61/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "eba92302a2861cdc0098cc54bc9f17cb2c47eb61",
      "sha256": "9d56d04b36d0fd12ff54ae4c5bac769cc176e254e64ff71144614b6318b40793",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "MixtralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 32768,
        "model_type": "mixtral",
        "num_attention_heads": 32,
        "num_experts_per_tok": 2,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "num_local_experts": 8,
        "output_router_logits": false,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000.0,
        "router_aux_loss_coef": 0.02,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.36.0.dev0",
        "use_cache": true,
        "vocab_size": 32000
      }
    },
    {
      "id": "mistralai/Mixtral-8x7B-v0.1",
      "catalogId": "mistralai--mixtral-8x7b-v0.1",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/mistralai/Mixtral-8x7B-v0.1/blob/fc7ac94680e38d7348cfa806e51218e6273104b0/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "fc7ac94680e38d7348cfa806e51218e6273104b0",
      "sha256": "9d56d04b36d0fd12ff54ae4c5bac769cc176e254e64ff71144614b6318b40793",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "MixtralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 32768,
        "model_type": "mixtral",
        "num_attention_heads": 32,
        "num_experts_per_tok": 2,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "num_local_experts": 8,
        "output_router_logits": false,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000.0,
        "router_aux_loss_coef": 0.02,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.36.0.dev0",
        "use_cache": true,
        "vocab_size": 32000
      }
    },
    {
      "id": "moonshotai/Kimi-Dev-72B",
      "catalogId": "moonshotai--kimi-dev-72b",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/moonshotai/Kimi-Dev-72B/blob/8791d7981945752a51f692d66f2bbfb3573c9722/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "8791d7981945752a51f692d66f2bbfb3573c9722",
      "sha256": "9c114c3da81d4db6027c0caab398b59fe800024df5a0ed27d341501575cecaf9",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 8192,
        "initializer_range": 0.02,
        "intermediate_size": 29568,
        "max_position_embeddings": 131072,
        "max_window_layers": 70,
        "model_type": "qwen2",
        "num_attention_heads": 64,
        "num_hidden_layers": 80,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 131072,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 152064
      }
    },
    {
      "id": "moonshotai/Kimi-K2-Base",
      "catalogId": "moonshotai--kimi-k2-base",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/moonshotai/Kimi-K2-Base/blob/ce72df012259dcc55d945e890f815fe7ef69159c/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "ce72df012259dcc55d945e890f815fe7ef69159c",
      "sha256": "8c13ae1049df55f29b3bdcae69a562433f243ff70dac251d819ecad8dbdf7439",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "DeepseekV3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV3Config",
          "AutoModel": "modeling_deepseek.DeepseekV3Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
        },
        "aux_loss_alpha": 0.001,
        "bos_token_id": 163584,
        "eos_token_id": 163585,
        "first_k_dense_replace": 1,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 18432,
        "kv_lora_rank": 512,
        "max_position_embeddings": 131072,
        "model_type": "kimi_k2",
        "moe_intermediate_size": 2048,
        "moe_layer_freq": 1,
        "n_group": 1,
        "n_routed_experts": 384,
        "n_shared_experts": 1,
        "norm_topk_prob": true,
        "num_attention_heads": 64,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 61,
        "num_key_value_heads": 64,
        "num_nextn_predict_layers": 0,
        "pretraining_tp": 1,
        "q_lora_rank": 1536,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "quantization_config": {
          "activation_scheme": "dynamic",
          "fmt": "e4m3",
          "quant_method": "fp8",
          "weight_block_size": [
            128,
            128
          ]
        },
        "rms_norm_eps": 1e-06,
        "rope_theta": 50000.0,
        "routed_scaling_factor": 2.827,
        "rope_scaling": {
          "beta_fast": 1.0,
          "beta_slow": 1.0,
          "factor": 32.0,
          "mscale": 1.0,
          "mscale_all_dim": 1.0,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "scoring_func": "sigmoid",
        "seq_aux": true,
        "tie_word_embeddings": false,
        "topk_group": 1,
        "topk_method": "noaux_tc",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.48.3",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 163840
      }
    },
    {
      "id": "moonshotai/Kimi-K2-Instruct",
      "catalogId": "moonshotai--kimi-k2-instruct",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/moonshotai/Kimi-K2-Instruct/blob/fd1984e2b7a3350dbf7305fe73a4ede25c14de50/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "fd1984e2b7a3350dbf7305fe73a4ede25c14de50",
      "sha256": "8c13ae1049df55f29b3bdcae69a562433f243ff70dac251d819ecad8dbdf7439",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "DeepseekV3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV3Config",
          "AutoModel": "modeling_deepseek.DeepseekV3Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
        },
        "aux_loss_alpha": 0.001,
        "bos_token_id": 163584,
        "eos_token_id": 163585,
        "first_k_dense_replace": 1,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 18432,
        "kv_lora_rank": 512,
        "max_position_embeddings": 131072,
        "model_type": "kimi_k2",
        "moe_intermediate_size": 2048,
        "moe_layer_freq": 1,
        "n_group": 1,
        "n_routed_experts": 384,
        "n_shared_experts": 1,
        "norm_topk_prob": true,
        "num_attention_heads": 64,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 61,
        "num_key_value_heads": 64,
        "num_nextn_predict_layers": 0,
        "pretraining_tp": 1,
        "q_lora_rank": 1536,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "quantization_config": {
          "activation_scheme": "dynamic",
          "fmt": "e4m3",
          "quant_method": "fp8",
          "weight_block_size": [
            128,
            128
          ]
        },
        "rms_norm_eps": 1e-06,
        "rope_theta": 50000.0,
        "routed_scaling_factor": 2.827,
        "rope_scaling": {
          "beta_fast": 1.0,
          "beta_slow": 1.0,
          "factor": 32.0,
          "mscale": 1.0,
          "mscale_all_dim": 1.0,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "scoring_func": "sigmoid",
        "seq_aux": true,
        "tie_word_embeddings": false,
        "topk_group": 1,
        "topk_method": "noaux_tc",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.48.3",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 163840
      }
    },
    {
      "id": "moonshotai/Kimi-K2-Instruct-0905",
      "catalogId": "moonshotai--kimi-k2-instruct-0905",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 262144,
      "status": "verified",
      "source": "https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905/blob/ac6c49f04883bd0a0598b790693a72061c676629/config.json",
      "max": 262144,
      "field": "max_position_embeddings",
      "revision": "ac6c49f04883bd0a0598b790693a72061c676629",
      "sha256": "4cd10b0f3cb1c1dfdbfcdd2f303057500f570b24f671ce5eb7650b6a511807cc",
      "evidence": {
        "max_position_embeddings": 262144
      },
      "config": {
        "_attn_implementation_autoset": false,
        "_name_or_path": "",
        "add_cross_attention": false,
        "architectures": [
          "DeepseekV3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV3Config",
          "AutoModel": "modeling_deepseek.DeepseekV3Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
        },
        "aux_loss_alpha": 0.001,
        "bad_words_ids": null,
        "begin_suppress_tokens": null,
        "bos_token_id": 163584,
        "chunk_size_feed_forward": 0,
        "cross_attention_hidden_size": null,
        "decoder_start_token_id": null,
        "diversity_penalty": 0.0,
        "do_sample": false,
        "early_stopping": false,
        "encoder_no_repeat_ngram_size": 0,
        "eos_token_id": 163585,
        "ep_size": 1,
        "exponential_decay_length_penalty": null,
        "finetuning_task": null,
        "first_k_dense_replace": 1,
        "forced_bos_token_id": null,
        "forced_eos_token_id": null,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "id2label": {
          "0": "LABEL_0",
          "1": "LABEL_1"
        },
        "initializer_range": 0.02,
        "intermediate_size": 18432,
        "is_decoder": false,
        "is_encoder_decoder": false,
        "kv_lora_rank": 512,
        "label2id": {
          "LABEL_0": 0,
          "LABEL_1": 1
        },
        "length_penalty": 1.0,
        "max_length": 20,
        "max_position_embeddings": 262144,
        "min_length": 0,
        "model_type": "kimi_k2",
        "moe_intermediate_size": 2048,
        "moe_layer_freq": 1,
        "n_group": 1,
        "n_routed_experts": 384,
        "n_shared_experts": 1,
        "no_repeat_ngram_size": 0,
        "norm_topk_prob": true,
        "num_attention_heads": 64,
        "num_beam_groups": 1,
        "num_beams": 1,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 61,
        "num_key_value_heads": 64,
        "num_nextn_predict_layers": 0,
        "num_return_sequences": 1,
        "output_attentions": false,
        "output_hidden_states": false,
        "output_scores": false,
        "pad_token_id": 163839,
        "prefix": null,
        "pretraining_tp": 1,
        "problem_type": null,
        "pruned_heads": {},
        "q_lora_rank": 1536,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "quantization_config": {
          "activation_scheme": "dynamic",
          "fmt": "e4m3",
          "quant_method": "fp8",
          "weight_block_size": [
            128,
            128
          ]
        },
        "remove_invalid_values": false,
        "repetition_penalty": 1.0,
        "return_dict": true,
        "return_dict_in_generate": false,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "beta_fast": 1.0,
          "beta_slow": 1.0,
          "factor": 64.0,
          "mscale": 1.0,
          "mscale_all_dim": 1.0,
          "original_max_position_embeddings": 4096,
          "type": "yarn"
        },
        "rope_theta": 50000.0,
        "routed_scaling_factor": 2.827,
        "scoring_func": "sigmoid",
        "sep_token_id": null,
        "seq_aux": true,
        "suppress_tokens": null,
        "task_specific_params": null,
        "temperature": 1.0,
        "tf_legacy_loss": false,
        "tie_encoder_decoder": false,
        "tie_word_embeddings": false,
        "tokenizer_class": null,
        "top_k": 50,
        "top_p": 1.0,
        "topk_group": 1,
        "topk_method": "noaux_tc",
        "torch_dtype": "bfloat16",
        "torchscript": false,
        "transformers_version": "4.51.3",
        "typical_p": 1.0,
        "use_bfloat16": false,
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 163840
      }
    },
    {
      "id": "moonshotai/Moonlight-16B-A3B",
      "catalogId": "moonshotai--moonlight-16b-a3b",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/moonshotai/Moonlight-16B-A3B/blob/476b36a473d4467f94469414bef6cee75c9c8172/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "476b36a473d4467f94469414bef6cee75c9c8172",
      "sha256": "64513a4aa6ffd2337215ea80c880491ad54a180ffb66a53dd9e178c6f8e9f76c",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "architectures": [
          "DeepseekV3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV3Config",
          "AutoModel": "modeling_deepseek.DeepseekV3Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
        },
        "aux_loss_alpha": 0.001,
        "bos_token_id": 163584,
        "eos_token_id": 163585,
        "ep_size": 1,
        "first_k_dense_replace": 1,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 11264,
        "kv_lora_rank": 512,
        "max_position_embeddings": 8192,
        "model_type": "deepseek_v3",
        "moe_intermediate_size": 1408,
        "moe_layer_freq": 1,
        "n_group": 1,
        "n_routed_experts": 64,
        "n_shared_experts": 2,
        "norm_topk_prob": true,
        "num_attention_heads": 16,
        "num_experts_per_tok": 6,
        "num_hidden_layers": 27,
        "num_key_value_heads": 16,
        "num_nextn_predict_layers": 0,
        "pretraining_tp": 1,
        "q_lora_rank": null,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "rms_norm_eps": 1e-05,
        "rope_theta": 50000.0,
        "routed_scaling_factor": 2.446,
        "scoring_func": "sigmoid",
        "seq_aux": true,
        "tie_word_embeddings": false,
        "topk_group": 1,
        "topk_method": "noaux_tc",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.3",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 163840
      }
    },
    {
      "id": "moonshotai/Moonlight-16B-A3B-Instruct",
      "catalogId": "moonshotai--moonlight-16b-a3b-instruct",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/moonshotai/Moonlight-16B-A3B-Instruct/blob/4e735b07a89f73647dfab71ab91b840f362ede5b/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "4e735b07a89f73647dfab71ab91b840f362ede5b",
      "sha256": "6827d4b5327a446d6a80716a6e5cec695f279b282110ef7dae09241656430302",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "architectures": [
          "DeepseekV3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "configuration_deepseek.DeepseekV3Config",
          "AutoModel": "modeling_deepseek.DeepseekV3Model",
          "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
        },
        "aux_loss_alpha": 0.001,
        "bos_token_id": 163584,
        "eos_token_id": 163586,
        "ep_size": 1,
        "first_k_dense_replace": 1,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 11264,
        "kv_lora_rank": 512,
        "max_position_embeddings": 8192,
        "model_type": "deepseek_v3",
        "moe_intermediate_size": 1408,
        "moe_layer_freq": 1,
        "n_group": 1,
        "n_routed_experts": 64,
        "n_shared_experts": 2,
        "norm_topk_prob": true,
        "num_attention_heads": 16,
        "num_experts_per_tok": 6,
        "num_hidden_layers": 27,
        "num_key_value_heads": 16,
        "num_nextn_predict_layers": 0,
        "pretraining_tp": 1,
        "q_lora_rank": null,
        "qk_nope_head_dim": 128,
        "qk_rope_head_dim": 64,
        "rms_norm_eps": 1e-05,
        "rope_theta": 50000.0,
        "routed_scaling_factor": 2.446,
        "scoring_func": "sigmoid",
        "seq_aux": true,
        "tie_word_embeddings": false,
        "topk_group": 1,
        "topk_method": "noaux_tc",
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.3",
        "use_cache": true,
        "v_head_dim": 128,
        "vocab_size": 163840
      }
    },
    {
      "id": "NousResearch/Hermes-2-Pro-Llama-3-8B",
      "catalogId": "nousresearch--hermes-2-pro-llama-3-8b",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B/blob/f798274b30e7d2d4797c369edcc0cc7473b6e6f2/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "f798274b30e7d2d4797c369edcc0cc7473b6e6f2",
      "sha256": "7e9f7d3a52077a957b5555b67c1fca9c0066cff03986a6ab7e49d5b05ef5827f",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "_name_or_path": "./hermes-2-pro-llama-3-8b-DPO",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 128000,
        "eos_token_id": 128003,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 8192,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 500000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "float16",
        "transformers_version": "4.40.1",
        "use_cache": true,
        "vocab_size": 128288
      }
    },
    {
      "id": "NousResearch/Hermes-2-Pro-Mistral-7B",
      "catalogId": "nousresearch--hermes-2-pro-mistral-7b",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B/blob/24dbda51d986efa05201eec7a093ac91fc5519cf/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "24dbda51d986efa05201eec7a093ac91fc5519cf",
      "sha256": "62e56b76e819edbc8472e0edf207657f03d1a6772c706b4f700f8e267718723b",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "_name_or_path": "bagel-hermes-2-pro-7b",
        "architectures": [
          "MistralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 32000,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 32768,
        "model_type": "mistral",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 10000.0,
        "sliding_window": 4096,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.38.2",
        "use_cache": false,
        "vocab_size": 32032
      }
    },
    {
      "id": "NousResearch/Hermes-2-Theta-Llama-3-70B",
      "catalogId": "nousresearch--hermes-2-theta-llama-3-70b",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-70B/blob/8948247fa83f3f970ad24b3394d5656507642922/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "8948247fa83f3f970ad24b3394d5656507642922",
      "sha256": "84a3b632143f4131957b7ccb364e1b95bdf3ffc1b48ba7651cc9d4c6db480a21",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "_name_or_path": "NousResearch/Hermes-2-Theta-Llama-3-70B",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 128000,
        "eos_token_id": 128003,
        "hidden_act": "silu",
        "hidden_size": 8192,
        "initializer_range": 0.02,
        "intermediate_size": 28672,
        "max_position_embeddings": 8192,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 64,
        "num_hidden_layers": 80,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 500000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.0.dev0",
        "use_cache": false,
        "vocab_size": 128256
      }
    },
    {
      "id": "NousResearch/Hermes-2-Theta-Llama-3-8B",
      "catalogId": "nousresearch--hermes-2-theta-llama-3-8b",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B/blob/57a73110702e7b05ba3f39fef36297454c680725/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "57a73110702e7b05ba3f39fef36297454c680725",
      "sha256": "b3dd2bfdfe64e4e281aa6457902bd13863337edff2aa57a3c62fb7443fa815ec",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "_name_or_path": "goddardexperiments/HermesProInstructV10",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 128000,
        "eos_token_id": 128003,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 8192,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 500000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.0.dev0",
        "use_cache": true,
        "vocab_size": 128256
      }
    },
    {
      "id": "NousResearch/Hermes-3-Llama-3.1-405B",
      "catalogId": "nousresearch--hermes-3-llama-3.1-405b",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B/blob/b9fe8ede1f5075f171b2c0a235e20ae4aba33767/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "b9fe8ede1f5075f171b2c0a235e20ae4aba33767",
      "sha256": "355d1e20fab58f54b5aba0beda4d9c1357b84c37b6bbc1ed9c4311f44b689e24",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-405B",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 128000,
        "eos_token_id": 128039,
        "hidden_act": "silu",
        "hidden_size": 16384,
        "initializer_range": 0.02,
        "intermediate_size": 53248,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 128,
        "num_hidden_layers": 126,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "factor": 8.0,
          "high_freq_factor": 4.0,
          "low_freq_factor": 1.0,
          "original_max_position_embeddings": 8192,
          "rope_type": "llama3"
        },
        "rope_theta": 500000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.0.dev0",
        "use_cache": true,
        "vocab_size": 128256
      }
    },
    {
      "id": "NousResearch/Hermes-3-Llama-3.1-70B",
      "catalogId": "nousresearch--hermes-3-llama-3.1-70b",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B/blob/1fc86da0ce9cdb14cd775ad270bc7d1b4bf70ede/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "1fc86da0ce9cdb14cd775ad270bc7d1b4bf70ede",
      "sha256": "44f58226b5054438665b9fea20a5f80165b5628ab6ff792efb55fb269a721c00",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "_name_or_path": "out/hermes-3-8k-llama-3.1-70b-chatml-1/checkpoint-3075/merged",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 128000,
        "eos_token_id": 128039,
        "hidden_act": "silu",
        "hidden_size": 8192,
        "initializer_range": 0.02,
        "intermediate_size": 28672,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 64,
        "num_hidden_layers": 80,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "factor": 8.0,
          "high_freq_factor": 4.0,
          "low_freq_factor": 1.0,
          "original_max_position_embeddings": 8192,
          "rope_type": "llama3"
        },
        "rope_theta": 500000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.0.dev0",
        "use_cache": true,
        "vocab_size": 128256
      }
    },
    {
      "id": "NousResearch/Hermes-3-Llama-3.1-8B",
      "catalogId": "nousresearch--hermes-3-llama-3.1-8b",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B/blob/896ea440e5a9e6070e3d8a2774daf2b481ab425b/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "896ea440e5a9e6070e3d8a2774daf2b481ab425b",
      "sha256": "7e189a0da074da6a878d5a276336caf3d62c57138f461bc6239402639f1bc6f5",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 128000,
        "eos_token_id": 128040,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "factor": 8.0,
          "high_freq_factor": 4.0,
          "low_freq_factor": 1.0,
          "original_max_position_embeddings": 8192,
          "rope_type": "llama3"
        },
        "rope_theta": 500000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.0.dev0",
        "use_cache": true,
        "vocab_size": 128256
      }
    },
    {
      "id": "NousResearch/Hermes-3-Llama-3.2-3B",
      "catalogId": "nousresearch--hermes-3-llama-3.2-3b",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Hermes-3-Llama-3.2-3B/blob/7f1a6bec8cdce6551014fd5bbeb4cd8c0f1fbeab/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "7f1a6bec8cdce6551014fd5bbeb4cd8c0f1fbeab",
      "sha256": "0358fd7dc3b04400cacdccfa44b0d461d8108d91bb80ba4813324f682eba9b8a",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "_name_or_path": "Nous-Research-Core/Hermes-3-Llama-3.2-3b-base-fft-chatml-rerun-8xh100-e4-2024-11-24-4k-steps",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 128000,
        "eos_token_id": 128039,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 24,
        "num_hidden_layers": 28,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "factor": 32.0,
          "high_freq_factor": 4.0,
          "low_freq_factor": 1.0,
          "original_max_position_embeddings": 8192,
          "rope_type": "llama3"
        },
        "rope_theta": 500000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.3",
        "use_cache": false,
        "vocab_size": 128256
      }
    },
    {
      "id": "NousResearch/Hermes-4-70B",
      "catalogId": "nousresearch--hermes-4-70b",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Hermes-4-70B/blob/d5dec2bd6b3930a09ddefd0b7fc6523fe0720d09/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "d5dec2bd6b3930a09ddefd0b7fc6523fe0720d09",
      "sha256": "0231071d7243ebc500f6deef9af1fe03fef1e1a830dfdbc6343fea4473895e7c",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 128000,
        "eos_token_id": 128001,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 8192,
        "initializer_range": 0.02,
        "intermediate_size": 28672,
        "max_position_embeddings": 131072,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 64,
        "num_hidden_layers": 80,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "factor": 8.0,
          "high_freq_factor": 4.0,
          "low_freq_factor": 1.0,
          "original_max_position_embeddings": 8192,
          "rope_type": "llama3"
        },
        "rope_theta": 500000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.52.4",
        "use_cache": true,
        "vocab_size": 128256
      }
    },
    {
      "id": "NousResearch/Nous-Hermes-2-Mistral-7B-DPO",
      "catalogId": "nousresearch--nous-hermes-2-mistral-7b-dpo",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO/blob/ebec0a691037d38955727d6949798429a63929dd/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "ebec0a691037d38955727d6949798429a63929dd",
      "sha256": "27e334d9edcba9f7e1cd704381475addbe8b9fd232040cff1d09f5806e524fb5",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
        "architectures": [
          "MistralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 32000,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 32768,
        "model_type": "mistral",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_theta": 10000.0,
        "sliding_window": 4096,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.0.dev0",
        "use_cache": false,
        "vocab_size": 32002
      }
    },
    {
      "id": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
      "catalogId": "nousresearch--nous-hermes-2-mixtral-8x7b-dpo",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO/blob/286ae6737d048ad1d965c2e830864df02db50f2f/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "286ae6737d048ad1d965c2e830864df02db50f2f",
      "sha256": "c4d525eaf1581fefa955e7c0d10b3e6a5eeb7cdda5a4485859c75fdc7f5ded59",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "_name_or_path": "NousResearch/OpenHermes-2.5-Mixtral-8x7B-epoch4",
        "architectures": [
          "MixtralForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 32000,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 32768,
        "model_type": "mixtral",
        "num_attention_heads": 32,
        "num_experts_per_tok": 2,
        "num_hidden_layers": 32,
        "num_key_value_heads": 8,
        "num_local_experts": 8,
        "output_router_logits": false,
        "rms_norm_eps": 1e-05,
        "rope_theta": 1000000.0,
        "router_aux_loss_coef": 0.02,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.0.dev0",
        "use_cache": false,
        "vocab_size": 32002
      }
    },
    {
      "id": "NousResearch/Nous-Hermes-2-SOLAR-10.7B",
      "catalogId": "nousresearch--nous-hermes-2-solar-10.7b",
      "checkedAt": "2026-09-28T06:57:56+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B/blob/14c1fbe2f71acdcd58247b30d5439bd572d52386/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "14c1fbe2f71acdcd58247b30d5439bd572d52386",
      "sha256": "118a51615372b2c43f0482149974533892b39e306fae33533a1afee1e652ebc4",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "_name_or_path": "upstage/SOLAR-10.7B-v1.0",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 32000,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 14336,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 48,
        "num_key_value_heads": 8,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.0.dev0",
        "use_cache": false,
        "vocab_size": 32002
      }
    },
    {
      "id": "NousResearch/Nous-Hermes-2-Yi-34B",
      "catalogId": "nousresearch--nous-hermes-2-yi-34b",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B/blob/fcb0a8847e76aea14aba9aa44009d4418ad7c18f/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "fcb0a8847e76aea14aba9aa44009d4418ad7c18f",
      "sha256": "ee9c6ff3c1a142ce1610b7fcf84417d4feb7f23c3e41bafdda3b75f2faed403b",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "_name_or_path": "01-ai/Yi-34B",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 1,
        "eos_token_id": 7,
        "hidden_act": "silu",
        "hidden_size": 7168,
        "initializer_range": 0.02,
        "intermediate_size": 20480,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 56,
        "num_hidden_layers": 60,
        "num_key_value_heads": 8,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 5000000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.37.0.dev0",
        "use_cache": false,
        "vocab_size": 64000
      }
    },
    {
      "id": "NousResearch/Nous-Hermes-llama-2-7b",
      "catalogId": "nousresearch--nous-hermes-llama-2-7b",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b/blob/cbd525ad0d5012e470c7696d5905345dc082e432/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "cbd525ad0d5012e470c7696d5905345dc082e432",
      "sha256": "b022cc2de37b3b3cd63f8d34022a4f42d2af66f6829dd823e6490f7126876035",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "_name_or_path": "output/hermes-llama2-4k/checkpoint-2259",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 32,
        "num_hidden_layers": 32,
        "num_key_value_heads": 32,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.32.0.dev0",
        "use_cache": false,
        "vocab_size": 32000
      }
    },
    {
      "id": "NousResearch/Nous-Hermes-Llama2-13b",
      "catalogId": "nousresearch--nous-hermes-llama2-13b",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b/blob/a5787bbb8ed8d322f3b1f91f9afd7fe07e7f041a/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "a5787bbb8ed8d322f3b1f91f9afd7fe07e7f041a",
      "sha256": "eeedc239a08a0ebed4192d09d7c8cd53d3ad76bd258692295621dfc1c527407c",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "_name_or_path": "output/hermes-llama2-4k/checkpoint-2259",
        "architectures": [
          "LlamaForCausalLM"
        ],
        "bos_token_id": 1,
        "eos_token_id": 2,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 13824,
        "max_position_embeddings": 4096,
        "model_type": "llama",
        "num_attention_heads": 40,
        "num_hidden_layers": 40,
        "num_key_value_heads": 40,
        "pad_token_id": 0,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.32.0.dev0",
        "use_cache": true,
        "vocab_size": 32032
      }
    },
    {
      "id": "openai/gpt-oss-120b",
      "catalogId": "openai--gpt-oss-120b",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/openai/gpt-oss-120b/blob/b5c939de8f754692c1647ca79fbf85e8c1e70f8a/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "b5c939de8f754692c1647ca79fbf85e8c1e70f8a",
      "sha256": "933aeb666a3fd851133ddd7686414f369bc564c4185fb5704416550879f10566",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GptOssForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "eos_token_id": 200002,
        "experts_per_token": 4,
        "head_dim": 64,
        "hidden_act": "silu",
        "hidden_size": 2880,
        "initial_context_length": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 2880,
        "layer_types": [
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention"
        ],
        "max_position_embeddings": 131072,
        "model_type": "gpt_oss",
        "num_attention_heads": 64,
        "num_experts_per_tok": 4,
        "num_hidden_layers": 36,
        "num_key_value_heads": 8,
        "num_local_experts": 128,
        "output_router_logits": false,
        "pad_token_id": 199999,
        "quantization_config": {
          "modules_to_not_convert": [
            "model.layers.*.self_attn",
            "model.layers.*.mlp.router",
            "model.embed_tokens",
            "lm_head"
          ],
          "quant_method": "mxfp4"
        },
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "beta_fast": 32.0,
          "beta_slow": 1.0,
          "factor": 32.0,
          "original_max_position_embeddings": 4096,
          "rope_type": "yarn",
          "truncate": false
        },
        "rope_theta": 150000,
        "router_aux_loss_coef": 0.9,
        "sliding_window": 128,
        "swiglu_limit": 7.0,
        "tie_word_embeddings": false,
        "transformers_version": "4.55.0.dev0",
        "use_cache": true,
        "vocab_size": 201088
      }
    },
    {
      "id": "openai/gpt-oss-20b",
      "catalogId": "openai--gpt-oss-20b",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/openai/gpt-oss-20b/blob/6cee5e81ee83917806bbde320786a8fb61efebee/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "6cee5e81ee83917806bbde320786a8fb61efebee",
      "sha256": "3a2a26ded679375b7928ddeca59764df7cea83220c1961035f6d6e232659e9ce",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GptOssForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "eos_token_id": 200002,
        "experts_per_token": 4,
        "head_dim": 64,
        "hidden_act": "silu",
        "hidden_size": 2880,
        "initial_context_length": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 2880,
        "layer_types": [
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention",
          "sliding_attention",
          "full_attention"
        ],
        "max_position_embeddings": 131072,
        "model_type": "gpt_oss",
        "num_attention_heads": 64,
        "num_experts_per_tok": 4,
        "num_hidden_layers": 24,
        "num_key_value_heads": 8,
        "num_local_experts": 32,
        "output_router_logits": false,
        "pad_token_id": 199999,
        "quantization_config": {
          "modules_to_not_convert": [
            "model.layers.*.self_attn",
            "model.layers.*.mlp.router",
            "model.embed_tokens",
            "lm_head"
          ],
          "quant_method": "mxfp4"
        },
        "rms_norm_eps": 1e-05,
        "rope_scaling": {
          "beta_fast": 32.0,
          "beta_slow": 1.0,
          "factor": 32.0,
          "original_max_position_embeddings": 4096,
          "rope_type": "yarn",
          "truncate": false
        },
        "rope_theta": 150000,
        "router_aux_loss_coef": 0.9,
        "sliding_window": 128,
        "swiglu_limit": 7.0,
        "tie_word_embeddings": false,
        "transformers_version": "4.55.0.dev0",
        "use_cache": true,
        "vocab_size": 201088
      }
    },
    {
      "id": "Qwen/Qwen2.5-0.5B",
      "catalogId": "qwen--qwen2.5-0.5b",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-0.5B/blob/060db6499f32faf8b98477b0a26969ef7d8b9987/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
      "sha256": "479dcf0c5286339e41ad3992cd08ae88a467c4187587936248e2b7c96283484b",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151643,
        "hidden_act": "silu",
        "hidden_size": 896,
        "initializer_range": 0.02,
        "intermediate_size": 4864,
        "max_position_embeddings": 32768,
        "max_window_layers": 24,
        "model_type": "qwen2",
        "num_attention_heads": 14,
        "num_hidden_layers": 24,
        "num_key_value_heads": 2,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 32768,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.40.1",
        "use_cache": true,
        "use_mrope": false,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen2.5-0.5B-Instruct",
      "catalogId": "qwen--qwen2.5-0.5b-instruct",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct/blob/7ae557604adf67be50417f59c2c2f167def9a775/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "7ae557604adf67be50417f59c2c2f167def9a775",
      "sha256": "18e18afcaccafade98daf13a54092927904649e1dd4eba8299ab717d5d94ff45",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 896,
        "initializer_range": 0.02,
        "intermediate_size": 4864,
        "max_position_embeddings": 32768,
        "max_window_layers": 21,
        "model_type": "qwen2",
        "num_attention_heads": 14,
        "num_hidden_layers": 24,
        "num_key_value_heads": 2,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 32768,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen2.5-1.5B-Instruct",
      "catalogId": "qwen--qwen2.5-1.5b-instruct",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct/blob/989aa7980e4cf806f80c7fef2b1adb7bc71aa306/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "989aa7980e4cf806f80c7fef2b1adb7bc71aa306",
      "sha256": "98d2ff8cc47488d08a2b0b3acf4eb99ef210779b42bd48605f6b8e36acdbf670",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 1536,
        "initializer_range": 0.02,
        "intermediate_size": 8960,
        "max_position_embeddings": 32768,
        "max_window_layers": 21,
        "model_type": "qwen2",
        "num_attention_heads": 12,
        "num_hidden_layers": 28,
        "num_key_value_heads": 2,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 32768,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen2.5-14B-Instruct",
      "catalogId": "qwen--qwen2.5-14b-instruct",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/cf98f3b3bbb457ad9e2bb7baf9a0125b6b88caa8/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "cf98f3b3bbb457ad9e2bb7baf9a0125b6b88caa8",
      "sha256": "0f2085dbbe2ee251bd6a6a0797d84a6ce34436044d629aa3cba793b43d311a9e",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 13824,
        "max_position_embeddings": 32768,
        "max_window_layers": 70,
        "model_type": "qwen2",
        "num_attention_heads": 40,
        "num_hidden_layers": 48,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 131072,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 152064
      }
    },
    {
      "id": "Qwen/Qwen2.5-32B-Instruct",
      "catalogId": "q32",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd",
      "sha256": "9c6772f138ef9e5b3d1c18f2c87e451bbc01f5f1a4eabb36f9bf4f53829b903e",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 27648,
        "max_position_embeddings": 32768,
        "max_window_layers": 70,
        "model_type": "qwen2",
        "num_attention_heads": 40,
        "num_hidden_layers": 64,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 131072,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 152064
      }
    },
    {
      "id": "Qwen/Qwen2.5-3B-Instruct",
      "catalogId": "qwen--qwen2.5-3b-instruct",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/aa8e72537993ba99e69dfaafa59ed015b17504d1/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "aa8e72537993ba99e69dfaafa59ed015b17504d1",
      "sha256": "eed00b17e22553979d090fa492e587e92885e328914c8e0b0b78f0a0d3576b3b",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 32768,
        "max_window_layers": 70,
        "model_type": "qwen2",
        "num_attention_heads": 16,
        "num_hidden_layers": 36,
        "num_key_value_heads": 2,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 32768,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen2.5-72B-Instruct",
      "catalogId": "q72",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/495f39366efef23836d0cfae4fbe635880d2be31/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "495f39366efef23836d0cfae4fbe635880d2be31",
      "sha256": "14ca217334fe0fd10148413592d68c99eeb33431ed89c1afa130fee560be2a29",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 8192,
        "initializer_range": 0.02,
        "intermediate_size": 29568,
        "max_position_embeddings": 32768,
        "max_window_layers": 70,
        "model_type": "qwen2",
        "num_attention_heads": 64,
        "num_hidden_layers": 80,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 131072,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 152064
      }
    },
    {
      "id": "Qwen/Qwen2.5-7B-Instruct",
      "catalogId": "q7",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/a09a35458c702b33eeacc393d103063234e8bc28/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "a09a35458c702b33eeacc393d103063234e8bc28",
      "sha256": "7463bb0ea78315365e6c6b74de4e73bbcc8359dfb0c5a737584e077d42c0b03c",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 3584,
        "initializer_range": 0.02,
        "intermediate_size": 18944,
        "max_position_embeddings": 32768,
        "max_window_layers": 28,
        "model_type": "qwen2",
        "num_attention_heads": 28,
        "num_hidden_layers": 28,
        "num_key_value_heads": 4,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 131072,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 152064
      }
    },
    {
      "id": "Qwen/Qwen2.5-Coder-0.5B-Instruct",
      "catalogId": "qwen--qwen2.5-coder-0.5b-instruct",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct/blob/ea3f2471cf1b1f0db85067f1ef93848e38e88c25/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "ea3f2471cf1b1f0db85067f1ef93848e38e88c25",
      "sha256": "b1e58593cd31852f7da5c2fc31ddf6135b9c066c0fd9177a4bbe95717083adff",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 896,
        "initializer_range": 0.02,
        "intermediate_size": 4864,
        "max_position_embeddings": 32768,
        "max_window_layers": 24,
        "model_type": "qwen2",
        "num_attention_heads": 14,
        "num_hidden_layers": 24,
        "num_key_value_heads": 2,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 32768,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen2.5-Coder-1.5B-Instruct",
      "catalogId": "qwen--qwen2.5-coder-1.5b-instruct",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct/blob/2e1fd397ee46e1388853d2af2c993145b0f1098a/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "2e1fd397ee46e1388853d2af2c993145b0f1098a",
      "sha256": "88f9a17863c05fb313515d2ff74b1098e0c35579f99068e32beda00618508ae0",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 1536,
        "initializer_range": 0.02,
        "intermediate_size": 8960,
        "max_position_embeddings": 32768,
        "max_window_layers": 28,
        "model_type": "qwen2",
        "num_attention_heads": 12,
        "num_hidden_layers": 28,
        "num_key_value_heads": 2,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 32768,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen2.5-Coder-14B-Instruct",
      "catalogId": "qwen--qwen2.5-coder-14b-instruct",
      "checkedAt": "2026-09-28T06:57:57+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct/blob/aedcc2d42b622764e023cf882b6652e646b95671/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "aedcc2d42b622764e023cf882b6652e646b95671",
      "sha256": "9051fe83840dcd3a0f7e9f5b3372fc3927419eb56983273eac2dc635a5da7eae",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 13824,
        "max_position_embeddings": 32768,
        "max_window_layers": 48,
        "model_type": "qwen2",
        "num_attention_heads": 40,
        "num_hidden_layers": 48,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 131072,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 152064
      }
    },
    {
      "id": "Qwen/Qwen2.5-Coder-32B-Instruct",
      "catalogId": "qwen--qwen2.5-coder-32b-instruct",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct/blob/381fc969f78efac66bc87ff7ddeadb7e73c218a7/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "381fc969f78efac66bc87ff7ddeadb7e73c218a7",
      "sha256": "9fb1473a47db69c00c02f365c7b9e9d84fd2163c687c63b5a31167ebb2b189a6",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 27648,
        "max_position_embeddings": 32768,
        "max_window_layers": 64,
        "model_type": "qwen2",
        "num_attention_heads": 40,
        "num_hidden_layers": 64,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 131072,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 152064
      }
    },
    {
      "id": "Qwen/Qwen2.5-Coder-3B-Instruct",
      "catalogId": "qwen--qwen2.5-coder-3b-instruct",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct/blob/488639f1ff808d1d3d0ba301aef8c11461451ec5/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "488639f1ff808d1d3d0ba301aef8c11461451ec5",
      "sha256": "8f85440a3222d18772e964b1ef0b4b1574a1c5e6260c99aa23fcddd05c28b8ae",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "max_position_embeddings": 32768,
        "max_window_layers": 36,
        "model_type": "qwen2",
        "num_attention_heads": 16,
        "num_hidden_layers": 36,
        "num_key_value_heads": 2,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 32768,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.43.1",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen2.5-Coder-7B-Instruct",
      "catalogId": "qwen--qwen2.5-coder-7b-instruct",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct/blob/c03e6d358207e414f1eca0bb1891e29f1db0e242/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "c03e6d358207e414f1eca0bb1891e29f1db0e242",
      "sha256": "c0242402ad6a13b331ea320feea8c7e3776ffb7a4eff0757b9cd667e116d9a28",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen2ForCausalLM"
        ],
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "hidden_act": "silu",
        "hidden_size": 3584,
        "initializer_range": 0.02,
        "intermediate_size": 18944,
        "max_position_embeddings": 32768,
        "max_window_layers": 28,
        "model_type": "qwen2",
        "num_attention_heads": 28,
        "num_hidden_layers": 28,
        "num_key_value_heads": 4,
        "rms_norm_eps": 1e-06,
        "rope_theta": 1000000.0,
        "sliding_window": 131072,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.44.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 152064
      }
    },
    {
      "id": "Qwen/Qwen3-0.6B",
      "catalogId": "qwen--qwen3-0.6b",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 40960,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-0.6B/blob/c1899de289a04d12100db370d81485cdf75e47ca/config.json",
      "max": 40960,
      "field": "max_position_embeddings",
      "revision": "c1899de289a04d12100db370d81485cdf75e47ca",
      "sha256": "660db3b73d788119c04535e48cf9be5f55bc3100841a718637ae695b442f27dd",
      "evidence": {
        "max_position_embeddings": 40960
      },
      "config": {
        "architectures": [
          "Qwen3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 1024,
        "initializer_range": 0.02,
        "intermediate_size": 3072,
        "max_position_embeddings": 40960,
        "max_window_layers": 28,
        "model_type": "qwen3",
        "num_attention_heads": 16,
        "num_hidden_layers": 28,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "sliding_window": null,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-1.7B",
      "catalogId": "qwen--qwen3-1.7b",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 40960,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-1.7B/blob/70d244cc86ccca08cf5af4e1e306ecf908b1ad5e/config.json",
      "max": 40960,
      "field": "max_position_embeddings",
      "revision": "70d244cc86ccca08cf5af4e1e306ecf908b1ad5e",
      "sha256": "1ddb5b89ebc90dcb417a45c213d818577e65976454d29385c8f6140771d95197",
      "evidence": {
        "max_position_embeddings": 40960
      },
      "config": {
        "architectures": [
          "Qwen3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 6144,
        "max_position_embeddings": 40960,
        "max_window_layers": 28,
        "model_type": "qwen3",
        "num_attention_heads": 16,
        "num_hidden_layers": 28,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "sliding_window": null,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-1.7B-Base",
      "catalogId": "qwen--qwen3-1.7b-base",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-1.7B-Base/blob/ea980cb0a6c2ae4b936e82123acc929f1cec04c1/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "ea980cb0a6c2ae4b936e82123acc929f1cec04c1",
      "sha256": "1bb33a92c3548fbc68b889b490e810440435253598835bd71dff0396060c12db",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151643,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 6144,
        "max_position_embeddings": 32768,
        "max_window_layers": 28,
        "model_type": "qwen3",
        "num_attention_heads": 16,
        "num_hidden_layers": 28,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "sliding_window": null,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-14B",
      "catalogId": "qwen--qwen3-14b",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 40960,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-14B/blob/40c069824f4251a91eefaf281ebe4c544efd3e18/config.json",
      "max": 40960,
      "field": "max_position_embeddings",
      "revision": "40c069824f4251a91eefaf281ebe4c544efd3e18",
      "sha256": "e73c3664ca09b10a673fef0c22e8a6b456201d49bd4713c9691f775720e8857a",
      "evidence": {
        "max_position_embeddings": 40960
      },
      "config": {
        "architectures": [
          "Qwen3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 17408,
        "max_position_embeddings": 40960,
        "max_window_layers": 40,
        "model_type": "qwen3",
        "num_attention_heads": 40,
        "num_hidden_layers": 40,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-235B-A22B",
      "catalogId": "qwen--qwen3-235b-a22b",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 40960,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-235B-A22B/blob/8efa61729e24bd65b1d152b5ab5409052aa80e65/config.json",
      "max": 40960,
      "field": "max_position_embeddings",
      "revision": "8efa61729e24bd65b1d152b5ab5409052aa80e65",
      "sha256": "0ecd5d6fe6f2db6739e4e36ab06b88ebe7bd013ef31b9583f43796059a2b23a4",
      "evidence": {
        "max_position_embeddings": 40960
      },
      "config": {
        "architectures": [
          "Qwen3MoeForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "decoder_sparse_step": 1,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 12288,
        "max_position_embeddings": 40960,
        "max_window_layers": 94,
        "mlp_only_layers": [],
        "model_type": "qwen3_moe",
        "moe_intermediate_size": 1536,
        "norm_topk_prob": true,
        "num_attention_heads": 64,
        "num_experts": 128,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 94,
        "num_key_value_heads": 4,
        "output_router_logits": false,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000000.0,
        "router_aux_loss_coef": 0.001,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-235B-A22B-Instruct-2507",
      "catalogId": "qwen--qwen3-235b-a22b-instruct-2507",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 262144,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507/blob/ac9c66cc9b46af7306746a9250f23d47083d689e/config.json",
      "max": 262144,
      "field": "max_position_embeddings",
      "revision": "ac9c66cc9b46af7306746a9250f23d47083d689e",
      "sha256": "ad59a339665ee1c68cbff06ac72c9e59f5183ebfaf3698c98737e003a870e9e2",
      "evidence": {
        "max_position_embeddings": 262144
      },
      "config": {
        "architectures": [
          "Qwen3MoeForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "decoder_sparse_step": 1,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 12288,
        "max_position_embeddings": 262144,
        "max_window_layers": 94,
        "mlp_only_layers": [],
        "model_type": "qwen3_moe",
        "moe_intermediate_size": 1536,
        "norm_topk_prob": true,
        "num_attention_heads": 64,
        "num_experts": 128,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 94,
        "num_key_value_heads": 4,
        "output_router_logits": false,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000,
        "router_aux_loss_coef": 0.001,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-30B-A3B",
      "catalogId": "qwen--qwen3-30b-a3b",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 40960,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/ad44e777bcd18fa416d9da3bd8f70d33ebb85d39/config.json",
      "max": 40960,
      "field": "max_position_embeddings",
      "revision": "ad44e777bcd18fa416d9da3bd8f70d33ebb85d39",
      "sha256": "2850ddb3bf7aecad20b611e2d44f3077fc8193f4827c93beddd4c02ad63c2297",
      "evidence": {
        "max_position_embeddings": 40960
      },
      "config": {
        "architectures": [
          "Qwen3MoeForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "decoder_sparse_step": 1,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 6144,
        "max_position_embeddings": 40960,
        "max_window_layers": 48,
        "mlp_only_layers": [],
        "model_type": "qwen3_moe",
        "moe_intermediate_size": 768,
        "norm_topk_prob": true,
        "num_attention_heads": 32,
        "num_experts": 128,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 48,
        "num_key_value_heads": 4,
        "output_router_logits": false,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000000.0,
        "router_aux_loss_coef": 0.001,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
      "catalogId": "qwen--qwen3-30b-a3b-instruct-2507",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 262144,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507/blob/0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe/config.json",
      "max": 262144,
      "field": "max_position_embeddings",
      "revision": "0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe",
      "sha256": "a1ee086a68d0cbfc87316da00ba4b8507bd1292978108e2496201a30a450f438",
      "evidence": {
        "max_position_embeddings": 262144
      },
      "config": {
        "architectures": [
          "Qwen3MoeForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "decoder_sparse_step": 1,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 6144,
        "max_position_embeddings": 262144,
        "max_window_layers": 48,
        "mlp_only_layers": [],
        "model_type": "qwen3_moe",
        "moe_intermediate_size": 768,
        "norm_topk_prob": true,
        "num_attention_heads": 32,
        "num_experts": 128,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 48,
        "num_key_value_heads": 4,
        "output_router_logits": false,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 10000000,
        "router_aux_loss_coef": 0.001,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-32B",
      "catalogId": "qwen--qwen3-32b",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 40960,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-32B/blob/9216db5781bf21249d130ec9da846c4624c16137/config.json",
      "max": 40960,
      "field": "max_position_embeddings",
      "revision": "9216db5781bf21249d130ec9da846c4624c16137",
      "sha256": "97e295b63283935788fac5e4f8860862a56d4089538cafc93f0431f2ebe483bb",
      "evidence": {
        "max_position_embeddings": 40960
      },
      "config": {
        "architectures": [
          "Qwen3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 25600,
        "max_position_embeddings": 40960,
        "max_window_layers": 64,
        "model_type": "qwen3",
        "num_attention_heads": 64,
        "num_hidden_layers": 64,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-4B",
      "catalogId": "qwen--qwen3-4b",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 40960,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-4B/blob/1cfa9a7208912126459214e8b04321603b3df60c/config.json",
      "max": 40960,
      "field": "max_position_embeddings",
      "revision": "1cfa9a7208912126459214e8b04321603b3df60c",
      "sha256": "8ba006f74fecfaaeb392872a60f4a480e7ec9860153d2e1b769ec81f9a147f8a",
      "evidence": {
        "max_position_embeddings": 40960
      },
      "config": {
        "architectures": [
          "Qwen3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 2560,
        "initializer_range": 0.02,
        "intermediate_size": 9728,
        "max_position_embeddings": 40960,
        "max_window_layers": 36,
        "model_type": "qwen3",
        "num_attention_heads": 32,
        "num_hidden_layers": 36,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "sliding_window": null,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-4B-Base",
      "catalogId": "qwen--qwen3-4b-base",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-4B-Base/blob/906bfd4b4dc7f14ee4320094d8b41684abff8539/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "906bfd4b4dc7f14ee4320094d8b41684abff8539",
      "sha256": "304b2545a258d35620f1d4bf46940c0471d9baa00715ff8e77f84c2fca5057c1",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Qwen3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151643,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 2560,
        "initializer_range": 0.02,
        "intermediate_size": 9728,
        "max_position_embeddings": 32768,
        "max_window_layers": 36,
        "model_type": "qwen3",
        "num_attention_heads": 32,
        "num_hidden_layers": 36,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "sliding_window": null,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-4B-Instruct-2507",
      "catalogId": "qwen--qwen3-4b-instruct-2507",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 262144,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/cdbee75f17c01a7cc42f958dc650907174af0554/config.json",
      "max": 262144,
      "field": "max_position_embeddings",
      "revision": "cdbee75f17c01a7cc42f958dc650907174af0554",
      "sha256": "5beea1a4a34c62782bfb2f911c606741a3bab8f92d80a118fa053c28af12e8ba",
      "evidence": {
        "max_position_embeddings": 262144
      },
      "config": {
        "architectures": [
          "Qwen3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 2560,
        "initializer_range": 0.02,
        "intermediate_size": 9728,
        "max_position_embeddings": 262144,
        "max_window_layers": 36,
        "model_type": "qwen3",
        "num_attention_heads": 32,
        "num_hidden_layers": 36,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 5000000,
        "sliding_window": null,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-8B",
      "catalogId": "qwen--qwen3-8b",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 40960,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-8B/blob/b968826d9c46dd6066d109eabc6255188de91218/config.json",
      "max": 40960,
      "field": "max_position_embeddings",
      "revision": "b968826d9c46dd6066d109eabc6255188de91218",
      "sha256": "f7c4eadfbbf522470667b797a3c89be2524832d2d599797248dc304fff447c30",
      "evidence": {
        "max_position_embeddings": 40960
      },
      "config": {
        "architectures": [
          "Qwen3ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 12288,
        "max_position_embeddings": 40960,
        "max_window_layers": 36,
        "model_type": "qwen3",
        "num_attention_heads": 32,
        "num_hidden_layers": 36,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
      "catalogId": "qwen--qwen3-coder-30b-a3b-instruct",
      "checkedAt": "2026-09-28T06:57:58+00:00",
      "previousMax": 262144,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/b2cff646eb4bb1d68355c01b18ae02e7cf42d120/config.json",
      "max": 262144,
      "field": "max_position_embeddings",
      "revision": "b2cff646eb4bb1d68355c01b18ae02e7cf42d120",
      "sha256": "e2c8d8eea39471785cd93379d8b48241ad7dcda299013155dd02526e34a0de62",
      "evidence": {
        "max_position_embeddings": 262144
      },
      "config": {
        "architectures": [
          "Qwen3MoeForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 151643,
        "decoder_sparse_step": 1,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 6144,
        "max_position_embeddings": 262144,
        "max_window_layers": 48,
        "mlp_only_layers": [],
        "model_type": "qwen3_moe",
        "moe_intermediate_size": 768,
        "norm_topk_prob": true,
        "num_attention_heads": 32,
        "num_experts": 128,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 48,
        "num_key_value_heads": 4,
        "output_router_logits": false,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 10000000,
        "router_aux_loss_coef": 0.001,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.52.3",
        "use_cache": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
      "catalogId": "qwen--qwen3-coder-480b-a35b-instruct",
      "checkedAt": "2026-09-28T06:57:59+00:00",
      "previousMax": 262144,
      "status": "verified",
      "source": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct/blob/9d90cf8fca1bf7b7acca42d3fc9ae694a2194069/config.json",
      "max": 262144,
      "field": "max_position_embeddings",
      "revision": "9d90cf8fca1bf7b7acca42d3fc9ae694a2194069",
      "sha256": "653230e2dd1c41bd1125d046f00259ed98d6294c75c63969f8890c6e139af7de",
      "evidence": {
        "max_position_embeddings": 262144
      },
      "config": {
        "architectures": [
          "Qwen3MoeForCausalLM"
        ],
        "attention_dropout": 0.0,
        "decoder_sparse_step": 1,
        "eos_token_id": 151645,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 6144,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "max_position_embeddings": 262144,
        "max_window_layers": 62,
        "mlp_only_layers": [],
        "model_type": "qwen3_moe",
        "moe_intermediate_size": 2560,
        "norm_topk_prob": true,
        "num_attention_heads": 96,
        "num_experts": 160,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 62,
        "num_key_value_heads": 8,
        "output_router_logits": false,
        "qkv_bias": false,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 10000000,
        "router_aux_loss_coef": 0.0,
        "shared_expert_intermediate_size": 0,
        "sliding_window": null,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.51.0",
        "use_cache": true,
        "use_qk_norm": true,
        "use_sliding_window": false,
        "vocab_size": 151936
      }
    },
    {
      "id": "tiiuae/falcon-11B",
      "catalogId": "tiiuae--falcon-11b",
      "checkedAt": "2026-09-28T06:57:59+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/tiiuae/falcon-11B/blob/a4ab868d7e8d53844009657bf7e755933ccccf8f/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "a4ab868d7e8d53844009657bf7e755933ccccf8f",
      "sha256": "32e1f275bb62c677923df9dd6785590838696b64cd5aa76580178fa2a5907074",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "_name_or_path": "tiiuae/falcon-11B",
        "activation": "gelu",
        "alibi": false,
        "architectures": [
          "FalconForCausalLM"
        ],
        "attention_dropout": 0.0,
        "auto_map": {
          "AutoConfig": "tiiuae/falcon-11B--configuration_falcon.FalconConfig",
          "AutoModel": "tiiuae/falcon-11B--modeling_falcon.FalconModel",
          "AutoModelForCausalLM": "tiiuae/falcon-11B--modeling_falcon.FalconForCausalLM",
          "AutoModelForQuestionAnswering": "tiiuae/falcon-11B--modeling_falcon.FalconForQuestionAnswering",
          "AutoModelForSequenceClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForSequenceClassification",
          "AutoModelForTokenClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForTokenClassification"
        },
        "bias": false,
        "bos_token_id": 11,
        "eos_token_id": 11,
        "ff_factor": 4,
        "ffn_hidden_size": 16384,
        "hidden_dropout": 0.0,
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "layer_norm_epsilon": 1e-05,
        "max_position_embeddings": 8192,
        "model_type": "falcon",
        "multi_query": true,
        "new_decoder_architecture": true,
        "num_attention_heads": 32,
        "num_hidden_layers": 60,
        "num_kv_heads": 8,
        "num_ln_in_parallel_attn": 1,
        "parallel_attn": true,
        "rope_scaling": null,
        "rope_theta": 500042.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.39.2",
        "use_cache": true,
        "vocab_size": 65024
      }
    },
    {
      "id": "tiiuae/falcon-40b",
      "catalogId": "tiiuae--falcon-40b",
      "checkedAt": "2026-09-28T06:57:59+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/tiiuae/falcon-40b",
      "configFetchNote": "ValueError: No explicit supported context field in config.json",
      "max": 2048,
      "field": "model-card.sequence-length",
      "evidence": {
        "sequenceLength": 2048
      },
      "revision": "05ab2ee8d6b593bdbab17d728de5c028a7a94d83",
      "sha256": "0ef334ad9485a02f8fa2168f8eae175444762183330817bf8d02ac6bb7beba96"
    },
    {
      "id": "tiiuae/falcon-7b",
      "catalogId": "tiiuae--falcon-7b",
      "checkedAt": "2026-09-28T06:57:59+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/tiiuae/falcon-7b",
      "configFetchNote": "ValueError: No explicit supported context field in config.json",
      "max": 2048,
      "field": "model-card.sequence-length",
      "evidence": {
        "sequenceLength": 2048
      },
      "revision": "ec89142b67d748a1865ea4451372db8313ada0d8",
      "sha256": "fcd19dd2a4e8d8398097b28ee7719d86752e55412b75453ef96d7c0f9c6419ed"
    },
    {
      "id": "tiiuae/falcon-7b-instruct",
      "catalogId": "tiiuae--falcon-7b-instruct",
      "checkedAt": "2026-09-28T06:57:59+00:00",
      "previousMax": 2048,
      "status": "verified",
      "source": "https://huggingface.co/tiiuae/falcon-7b-instruct",
      "configFetchNote": "ValueError: No explicit supported context field in config.json",
      "max": 2048,
      "field": "model-card.sequence-length",
      "evidence": {
        "sequenceLength": 2048
      },
      "revision": "8782b5c5d8c9290412416618f36a133653e85285",
      "sha256": "e33dcaabef48da484eb00cab453c15a8a274a8c92b41116b3393fbe660a4f287"
    },
    {
      "id": "tiiuae/Falcon3-10B-Base",
      "catalogId": "tiiuae--falcon3-10b-base",
      "checkedAt": "2026-09-28T06:57:59+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/tiiuae/Falcon3-10B-Base/blob/34bb99a889fe0426412da3dd2b46e6f64c8fd003/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "34bb99a889fe0426412da3dd2b46e6f64c8fd003",
      "sha256": "c2a1e6513eb01c2b8fee330fed72cc65b9e45452beec4e24f3cfb5f8ab898eaa",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "eos_token_id": 11,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "initializer_range": 0.02,
        "intermediate_size": 23040,
        "max_position_embeddings": 32768,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 12,
        "num_hidden_layers": 40,
        "num_key_value_heads": 4,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000042,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.1",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "tiiuae/Falcon3-10B-Instruct",
      "catalogId": "tiiuae--falcon3-10b-instruct",
      "checkedAt": "2026-09-28T06:57:59+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/tiiuae/Falcon3-10B-Instruct/blob/8799bc6aec0152757221dc6b272d824642db6202/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "8799bc6aec0152757221dc6b272d824642db6202",
      "sha256": "3192d1e0593446cb03d71705b446f4f674f077076c2931f91ff76d49f934cc26",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 11,
        "eos_token_id": 11,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "intermediate_size": 23040,
        "max_position_embeddings": 32768,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 12,
        "num_hidden_layers": 40,
        "num_key_value_heads": 4,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000042,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.1",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "tiiuae/Falcon3-1B-Base",
      "catalogId": "tiiuae--falcon3-1b-base",
      "checkedAt": "2026-09-28T06:57:59+00:00",
      "previousMax": 4096,
      "status": "verified",
      "source": "https://huggingface.co/tiiuae/Falcon3-1B-Base/blob/cb37ef3559b157b5c9d9226296ba01a5162da1f7/config.json",
      "max": 4096,
      "field": "max_position_embeddings",
      "revision": "cb37ef3559b157b5c9d9226296ba01a5162da1f7",
      "sha256": "b9be6e41dc8db67b2343521be7e5696d827685bf868243fccc6157b528be8cea",
      "evidence": {
        "max_position_embeddings": 4096
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "activation": "swiglu",
        "attention_bias": false,
        "attention_dropout": 0.0,
        "eos_token_id": 11,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "intermediate_size": 8192,
        "max_position_embeddings": 4096,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 8,
        "num_hidden_layers": 18,
        "num_key_value_heads": 4,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000042,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.1",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "tiiuae/Falcon3-1B-Instruct",
      "catalogId": "tiiuae--falcon3-1b-instruct",
      "checkedAt": "2026-09-28T06:57:59+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/tiiuae/Falcon3-1B-Instruct/blob/28ba2251970a01dd1edc7ba7dad2eb71216ccfdf/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "28ba2251970a01dd1edc7ba7dad2eb71216ccfdf",
      "sha256": "8a037915db0c54dfbed9a734868bacb684ab1dea7bcbb3964e2fc637da113b3b",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "eos_token_id": 11,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "max_position_embeddings": 8192,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 8,
        "num_hidden_layers": 18,
        "num_key_value_heads": 4,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000042,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.1",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "tiiuae/Falcon3-3B-Base",
      "catalogId": "tiiuae--falcon3-3b-base",
      "checkedAt": "2026-09-28T06:57:59+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/tiiuae/Falcon3-3B-Base/blob/092c29e3114ff551bd06b93b85424cdb525d227c/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "092c29e3114ff551bd06b93b85424cdb525d227c",
      "sha256": "6683fbccd54b8164cc987e3f7c88819cbac89eaaaab2b7c1f7572bc358fbd099",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "activation": "swiglu",
        "attention_bias": false,
        "attention_dropout": 0.0,
        "eos_token_id": 11,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "intermediate_size": 9216,
        "max_position_embeddings": 32768,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 12,
        "num_hidden_layers": 22,
        "num_key_value_heads": 4,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000042,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.1",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "tiiuae/Falcon3-3B-Instruct",
      "catalogId": "tiiuae--falcon3-3b-instruct",
      "checkedAt": "2026-09-28T06:57:59+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/tiiuae/Falcon3-3B-Instruct/blob/411bb94318f94f7a5735b77109f456b1e74b42a1/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "411bb94318f94f7a5735b77109f456b1e74b42a1",
      "sha256": "086ad14ee022bd8c7d0bff64fc49d96d8fc5051b467ecbef64bf97a192708e0c",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "eos_token_id": 11,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "initializer_range": 0.02,
        "intermediate_size": 9216,
        "max_position_embeddings": 32768,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 12,
        "num_hidden_layers": 22,
        "num_key_value_heads": 4,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000042,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.1",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "tiiuae/Falcon3-7B-Base",
      "catalogId": "tiiuae--falcon3-7b-base",
      "checkedAt": "2026-09-28T06:57:59+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/tiiuae/Falcon3-7B-Base/blob/bf3d7ed586cb22a921520e2d681a9d3d7642cde8/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "bf3d7ed586cb22a921520e2d681a9d3d7642cde8",
      "sha256": "5e9612ae5bb5938e906c84825e247b96ab11c8998fb51e7ae44622c898e43e79",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "eos_token_id": 11,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "initializer_range": 0.02,
        "intermediate_size": 23040,
        "max_position_embeddings": 32768,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 12,
        "num_hidden_layers": 28,
        "num_key_value_heads": 4,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000042,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.1",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "tiiuae/Falcon3-7B-Instruct",
      "catalogId": "tiiuae--falcon3-7b-instruct",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/tiiuae/Falcon3-7B-Instruct/blob/1e57a0ecd176c7c139f289c60a74e57f887c3dfb/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "1e57a0ecd176c7c139f289c60a74e57f887c3dfb",
      "sha256": "7a8b434b91929e25bc2b96a5adf2b29f8e822a8bdbd249ce1fb09e2fa12beda7",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bos_token_id": 11,
        "eos_token_id": 11,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "intermediate_size": 23040,
        "max_position_embeddings": 32768,
        "mlp_bias": false,
        "model_type": "llama",
        "num_attention_heads": 12,
        "num_hidden_layers": 28,
        "num_key_value_heads": 4,
        "pretraining_tp": 1,
        "rms_norm_eps": 1e-06,
        "rope_scaling": null,
        "rope_theta": 1000042,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.1",
        "use_cache": true,
        "vocab_size": 131072
      }
    },
    {
      "id": "zai-org/GLM-4-32B-0414",
      "catalogId": "zai-org--glm-4-32b-0414",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/GLM-4-32B-0414/blob/077b5c2f5c43bd3239fd605a0600229e8facbd4a/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "077b5c2f5c43bd3239fd605a0600229e8facbd4a",
      "sha256": "d39fa377eb7e712d0ba5934d54a30dc6ab7c25b44a515d4a435f3956dcad07e2",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Glm4ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "eos_token_id": [
          151329,
          151336,
          151338
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 6144,
        "initializer_range": 0.02,
        "intermediate_size": 23040,
        "max_position_embeddings": 32768,
        "model_type": "glm4",
        "num_attention_heads": 48,
        "num_hidden_layers": 61,
        "num_key_value_heads": 2,
        "pad_token_id": 151329,
        "partial_rotary_factor": 0.5,
        "rms_norm_eps": 1e-05,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.52.0.dev0",
        "use_cache": true,
        "vocab_size": 151552
      }
    },
    {
      "id": "zai-org/GLM-4-9B-0414",
      "catalogId": "zai-org--glm-4-9b-0414",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/GLM-4-9B-0414/blob/645b8482494e31b6b752272bf7f7f273ef0f3caf/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "645b8482494e31b6b752272bf7f7f273ef0f3caf",
      "sha256": "98794d8150da03ca7baec63208584810d01caf43427e376071c00e770f4b4fa7",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Glm4ForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "eos_token_id": [
          151329,
          151336,
          151338
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 13696,
        "max_position_embeddings": 32768,
        "model_type": "glm4",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 2,
        "pad_token_id": 151329,
        "partial_rotary_factor": 0.5,
        "rms_norm_eps": 1e-05,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.52.0.dev0",
        "use_cache": true,
        "vocab_size": 151552
      }
    },
    {
      "id": "zai-org/glm-4-9b-chat-hf",
      "catalogId": "zai-org--glm-4-9b-chat-hf",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/glm-4-9b-chat-hf/blob/8599336fc6c125203efb2360bfaf4c80eef1d1bf/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "8599336fc6c125203efb2360bfaf4c80eef1d1bf",
      "sha256": "8ec64bc0dff4835a800b9eceb059e2b8263f783c898812175aa1ccdda074f596",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "GlmForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "eos_token_id": [
          151329,
          151336,
          151338
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 13696,
        "max_position_embeddings": 131072,
        "model_type": "glm",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 2,
        "pad_token_id": 151329,
        "rms_norm_eps": 1.5625e-07,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.0.dev0",
        "use_cache": true,
        "vocab_size": 151552
      }
    },
    {
      "id": "zai-org/glm-4-9b-hf",
      "catalogId": "zai-org--glm-4-9b-hf",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/glm-4-9b-hf/blob/b44e98fcc8df0faba03a48b405356af6b91821e7/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "b44e98fcc8df0faba03a48b405356af6b91821e7",
      "sha256": "5b011cc64d25de710b395ad1249d79c5d6f4c00a481ac889a7ba48d230c30e02",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "architectures": [
          "GlmForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "eos_token_id": [
          151329,
          151336,
          151338
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 13696,
        "max_position_embeddings": 8192,
        "model_type": "glm",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 2,
        "pad_token_id": 151329,
        "rms_norm_eps": 1.5625e-07,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.46.0.dev0",
        "use_cache": true,
        "vocab_size": 151552
      }
    },
    {
      "id": "zai-org/GLM-4.5",
      "catalogId": "zai-org--glm-4.5",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/GLM-4.5/blob/cbb2c7cfb52fa128a9660cb1a7a78e017899e115/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "cbb2c7cfb52fa128a9660cb1a7a78e017899e115",
      "sha256": "a5dbd07371a8a51b0013a63a7a70543a7094af1a9598812b537133e6da78dda7",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "Glm4MoeForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "pad_token_id": 151329,
        "eos_token_id": [
          151329,
          151336,
          151338
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "partial_rotary_factor": 0.5,
        "initializer_range": 0.02,
        "intermediate_size": 12288,
        "max_position_embeddings": 131072,
        "model_type": "glm4_moe",
        "moe_intermediate_size": 1536,
        "norm_topk_prob": true,
        "num_attention_heads": 96,
        "n_group": 1,
        "topk_group": 1,
        "n_routed_experts": 160,
        "n_shared_experts": 1,
        "routed_scaling_factor": 2.5,
        "num_experts_per_tok": 8,
        "first_k_dense_replace": 3,
        "num_hidden_layers": 92,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "num_nextn_predict_layers": 1,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.54.0",
        "use_cache": true,
        "use_qk_norm": true,
        "vocab_size": 151552
      }
    },
    {
      "id": "zai-org/GLM-4.5-Air",
      "catalogId": "zai-org--glm-4.5-air",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/GLM-4.5-Air/blob/a24ceef6ce4f3536971efe9b778bdaa1bab18daa/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "a24ceef6ce4f3536971efe9b778bdaa1bab18daa",
      "sha256": "e59f21d7be4b4b917d80bb3a2d1211356d29cf3aeff93372523daf7d0ffb839d",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "Glm4MoeForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "pad_token_id": 151329,
        "eos_token_id": [
          151329,
          151336,
          151338
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "partial_rotary_factor": 0.5,
        "initializer_range": 0.02,
        "intermediate_size": 10944,
        "max_position_embeddings": 131072,
        "model_type": "glm4_moe",
        "moe_intermediate_size": 1408,
        "norm_topk_prob": true,
        "num_attention_heads": 96,
        "n_group": 1,
        "topk_group": 1,
        "n_routed_experts": 128,
        "n_shared_experts": 1,
        "routed_scaling_factor": 1.0,
        "num_experts_per_tok": 8,
        "first_k_dense_replace": 1,
        "num_hidden_layers": 46,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "num_nextn_predict_layers": 1,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.54.0",
        "use_cache": true,
        "use_qk_norm": false,
        "vocab_size": 151552
      }
    },
    {
      "id": "zai-org/GLM-4.5-Air-Base",
      "catalogId": "zai-org--glm-4.5-air-base",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 131072,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/GLM-4.5-Air-Base/blob/888c873d4eca81f28d0ef420aa2d96457c28b959/config.json",
      "max": 131072,
      "field": "max_position_embeddings",
      "revision": "888c873d4eca81f28d0ef420aa2d96457c28b959",
      "sha256": "e59f21d7be4b4b917d80bb3a2d1211356d29cf3aeff93372523daf7d0ffb839d",
      "evidence": {
        "max_position_embeddings": 131072
      },
      "config": {
        "architectures": [
          "Glm4MoeForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "pad_token_id": 151329,
        "eos_token_id": [
          151329,
          151336,
          151338
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "partial_rotary_factor": 0.5,
        "initializer_range": 0.02,
        "intermediate_size": 10944,
        "max_position_embeddings": 131072,
        "model_type": "glm4_moe",
        "moe_intermediate_size": 1408,
        "norm_topk_prob": true,
        "num_attention_heads": 96,
        "n_group": 1,
        "topk_group": 1,
        "n_routed_experts": 128,
        "n_shared_experts": 1,
        "routed_scaling_factor": 1.0,
        "num_experts_per_tok": 8,
        "first_k_dense_replace": 1,
        "num_hidden_layers": 46,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "num_nextn_predict_layers": 1,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.54.0",
        "use_cache": true,
        "use_qk_norm": false,
        "vocab_size": 151552
      }
    },
    {
      "id": "zai-org/GLM-4.6",
      "catalogId": "zai-org--glm-4.6",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 202752,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/GLM-4.6/blob/be72194883d968d7923a07e2f61681ea9a2826d1/config.json",
      "max": 202752,
      "field": "max_position_embeddings",
      "revision": "be72194883d968d7923a07e2f61681ea9a2826d1",
      "sha256": "f713924a536ac1965d8af2a3144d3a0ce0acae94f0fbfd7407240cbafcb08c53",
      "evidence": {
        "max_position_embeddings": 202752
      },
      "config": {
        "architectures": [
          "Glm4MoeForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "pad_token_id": 151329,
        "eos_token_id": [
          151329,
          151336,
          151338
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "partial_rotary_factor": 0.5,
        "initializer_range": 0.02,
        "intermediate_size": 12288,
        "max_position_embeddings": 202752,
        "model_type": "glm4_moe",
        "moe_intermediate_size": 1536,
        "norm_topk_prob": true,
        "num_attention_heads": 96,
        "n_group": 1,
        "topk_group": 1,
        "n_routed_experts": 160,
        "n_shared_experts": 1,
        "routed_scaling_factor": 2.5,
        "num_experts_per_tok": 8,
        "first_k_dense_replace": 3,
        "num_hidden_layers": 92,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "num_nextn_predict_layers": 1,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.54.0",
        "use_cache": true,
        "use_qk_norm": true,
        "vocab_size": 151552
      }
    },
    {
      "id": "zai-org/GLM-4.7",
      "catalogId": "zai-org--glm-4.7",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 202752,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/GLM-4.7/blob/602d01efcdd332c5238ca4bcede555defbe83eb7/config.json",
      "max": 202752,
      "field": "max_position_embeddings",
      "revision": "602d01efcdd332c5238ca4bcede555defbe83eb7",
      "sha256": "f713924a536ac1965d8af2a3144d3a0ce0acae94f0fbfd7407240cbafcb08c53",
      "evidence": {
        "max_position_embeddings": 202752
      },
      "config": {
        "architectures": [
          "Glm4MoeForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "pad_token_id": 151329,
        "eos_token_id": [
          151329,
          151336,
          151338
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "partial_rotary_factor": 0.5,
        "initializer_range": 0.02,
        "intermediate_size": 12288,
        "max_position_embeddings": 202752,
        "model_type": "glm4_moe",
        "moe_intermediate_size": 1536,
        "norm_topk_prob": true,
        "num_attention_heads": 96,
        "n_group": 1,
        "topk_group": 1,
        "n_routed_experts": 160,
        "n_shared_experts": 1,
        "routed_scaling_factor": 2.5,
        "num_experts_per_tok": 8,
        "first_k_dense_replace": 3,
        "num_hidden_layers": 92,
        "num_key_value_heads": 8,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 1000000,
        "num_nextn_predict_layers": 1,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.54.0",
        "use_cache": true,
        "use_qk_norm": true,
        "vocab_size": 151552
      }
    },
    {
      "id": "zai-org/glm-edge-1.5b-chat",
      "catalogId": "zai-org--glm-edge-1.5b-chat",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/glm-edge-1.5b-chat/blob/7b201d3c160c25beda4cf0d107617ad975cd1ca8/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "7b201d3c160c25beda4cf0d107617ad975cd1ca8",
      "sha256": "cac06b36fc4fdcee4e40687a4a4550184f7c6367191f1e0988b6d993352d8b14",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "architectures": [
          "GlmForCausalLM"
        ],
        "partial_rotary_factor": 1.0,
        "attention_bias": false,
        "attention_dropout": 0.0,
        "eos_token_id": [
          59246,
          59253,
          59255
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "intermediate_size": 6144,
        "max_position_embeddings": 8192,
        "model_type": "glm",
        "num_attention_heads": 16,
        "num_hidden_layers": 28,
        "num_key_value_heads": 4,
        "pad_token_id": 59246,
        "rms_norm_eps": 1e-05,
        "rope_theta": 10000.0,
        "tie_word_embeddings": true,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.47.0.dev0",
        "use_cache": true,
        "vocab_size": 59264
      }
    },
    {
      "id": "zai-org/glm-edge-4b-chat",
      "catalogId": "zai-org--glm-edge-4b-chat",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 8192,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/glm-edge-4b-chat/blob/a1817f2ab339ecdd8497c4d752ea71a65299f29a/config.json",
      "max": 8192,
      "field": "max_position_embeddings",
      "revision": "a1817f2ab339ecdd8497c4d752ea71a65299f29a",
      "sha256": "03b7e94daa7278951da9e80df8e45a80bc9f9aaa768ac19f21dc69575813bbd9",
      "evidence": {
        "max_position_embeddings": 8192
      },
      "config": {
        "architectures": [
          "GlmForCausalLM"
        ],
        "partial_rotary_factor": 1.0,
        "attention_bias": false,
        "attention_dropout": 0.0,
        "eos_token_id": [
          59246,
          59253,
          59255
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 3072,
        "initializer_range": 0.02,
        "intermediate_size": 8192,
        "max_position_embeddings": 8192,
        "model_type": "glm",
        "num_attention_heads": 24,
        "num_hidden_layers": 40,
        "num_key_value_heads": 6,
        "pad_token_id": 59246,
        "rms_norm_eps": 1e-05,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.47.0.dev0",
        "use_cache": true,
        "vocab_size": 59264
      }
    },
    {
      "id": "zai-org/GLM-Z1-32B-0414",
      "catalogId": "zai-org--glm-z1-32b-0414",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/GLM-Z1-32B-0414/blob/8eb2858992c1f749e2a6d4075455decc2484722d/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "8eb2858992c1f749e2a6d4075455decc2484722d",
      "sha256": "d39fa377eb7e712d0ba5934d54a30dc6ab7c25b44a515d4a435f3956dcad07e2",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Glm4ForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "eos_token_id": [
          151329,
          151336,
          151338
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 6144,
        "initializer_range": 0.02,
        "intermediate_size": 23040,
        "max_position_embeddings": 32768,
        "model_type": "glm4",
        "num_attention_heads": 48,
        "num_hidden_layers": 61,
        "num_key_value_heads": 2,
        "pad_token_id": 151329,
        "partial_rotary_factor": 0.5,
        "rms_norm_eps": 1e-05,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.52.0.dev0",
        "use_cache": true,
        "vocab_size": 151552
      }
    },
    {
      "id": "zai-org/GLM-Z1-9B-0414",
      "catalogId": "zai-org--glm-z1-9b-0414",
      "checkedAt": "2026-09-28T06:58:00+00:00",
      "previousMax": 32768,
      "status": "verified",
      "source": "https://huggingface.co/zai-org/GLM-Z1-9B-0414/blob/b221b06fefb23ca320922cf6e68ab5f2fb82de81/config.json",
      "max": 32768,
      "field": "max_position_embeddings",
      "revision": "b221b06fefb23ca320922cf6e68ab5f2fb82de81",
      "sha256": "98794d8150da03ca7baec63208584810d01caf43427e376071c00e770f4b4fa7",
      "evidence": {
        "max_position_embeddings": 32768
      },
      "config": {
        "architectures": [
          "Glm4ForCausalLM"
        ],
        "attention_bias": true,
        "attention_dropout": 0.0,
        "eos_token_id": [
          151329,
          151336,
          151338
        ],
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 13696,
        "max_position_embeddings": 32768,
        "model_type": "glm4",
        "num_attention_heads": 32,
        "num_hidden_layers": 40,
        "num_key_value_heads": 2,
        "pad_token_id": 151329,
        "partial_rotary_factor": 0.5,
        "rms_norm_eps": 1e-05,
        "rope_theta": 10000.0,
        "tie_word_embeddings": false,
        "torch_dtype": "bfloat16",
        "transformers_version": "4.52.0.dev0",
        "use_cache": true,
        "vocab_size": 151552
      }
    }
  ]
}
