config.json

{
  "architectures": [
    "GPTForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "config.GPTConfig",
    "AutoModelForCausalLM": "model.GPTForCausalLM"
  },
  "block_size": 512,
  "dtype": "float32",
  "feature_digit_token_ids": [
    20,
    21,
    22,
    23,
    24,
    25,
    26,
    27,
    28,
    29
  ],
  "feature_equals_token_id": 33,
  "feature_space_token_ids": [
    202,
    204,
    205,
    221,
    222,
    223,
    224,
    225,
    273,
    293,
    355,
    359,
    488,
    501,
    669,
    809,
    856,
    902,
    1168,
    1386,
    1407,
    1581,
    1687,
    2070,
    2165,
    2627,
    2951,
    3033,
    3218,
    3391,
    4076
  ],
  "head_dim": 48,
  "hidden_size": 192,
  "intermediate_size": 480,
  "labels_are_shifted": true,
  "max_position_embeddings": 512,
  "model_type": "gpt",
  "num_attention_heads": 4,
  "num_hidden_layers": 5,
  "num_key_value_heads": 2,
  "place_vocab_size": 66,
  "rms_norm_eps": 1e-06,
  "role_vocab_size": 12,
  "rope_theta": 5000.0,
  "transformers_version": "4.57.6",
  "use_place_embeddings": true,
  "use_role_embeddings": true,
  "vocab_size": 4096,
  "xsa_projection": true
}