{
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "model_type": "gpt2",
  "vocab_size": 16000,
  "n_positions": 256,
  "n_ctx": 256,
  "n_embd": 1024,
  "n_layer": 16,
  "n_head": 16,
  "n_inner": 4096,
  "activation_function": "gelu",
  "resid_pdrop": 0.1,
  "embd_pdrop": 0.1,
  "attn_pdrop": 0.1,
  "layer_norm_epsilon": 1e-05,
  "initializer_range": 0.02,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 3,
  "use_cache": true,
  "tie_word_embeddings": true
}