{
  "activation_dropout": 0.0,
  "activation_function": "relu",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "attention_dropout": 0.0,
  "attn_pdrop": 0.1,
  "bos_token_id": 2,
  "do_layer_norm_before": true,
  "dropout": 0.1,
  "dtype": "float16",
  "embd_pdrop": 0.1,
  "eos_token_id": 2,
  "ffn_dim": 3072,
  "init_std": 0.02,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "layerdrop": 0.0,
  "model_type": "gpt2",
  "n_embd": 768,
  "n_head": 12,
  "n_inner": null,
  "n_layer": 12,
  "n_positions": 2048,
  "pad_token_id": 1,
  "prefix": "</s>",
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0.1,
  "scale_attn_by_inverse_layer_idx": false,
  "scale_attn_weights": true,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "transformers_version": "4.56.1",
  "use_cache": true,
  "vocab_size": 50272,
  "word_embed_proj_dim": 768
}