{
  "model_type": "gpt2",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 2,
  "vocab_size": 5000,
  "n_positions": 256,
  "n_ctx": 256,
  "n_embd": 384,
  "n_layer": 6,
  "n_head": 6,
  "activation_function": "gelu_new",
  "resid_pdrop": 0.0,
  "embd_pdrop": 0.0,
  "attn_pdrop": 0.0,
  "layer_norm_epsilon": 1e-05,
  "use_cache": true
}