{
  "architectures": [
    "BigBrainLanguageModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_probability": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-06,
  "max_position_embeddings": 512,
  "model_type": "big-brain-lm",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "rope_theta": 10000,
  "sos_token_id": 0,
  "torch_dtype": "float32",
  "transformers_version": "4.31.0",
  "unk_token_id": 3,
  "vocab_size": 50265
}