{
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "model_type": "gpt2",
  "vocab_size": 256,
  "n_positions": 64,
  "n_embd": 32,
  "n_layer": 2,
  "n_head": 4,
  "n_inner": 128,
  "activation_function": "gelu_new",
  "resid_pdrop": 0.1,
  "embd_pdrop": 0.1,
  "attn_pdrop": 0.1,
  "layer_norm_epsilon": 1e-05,
  "initializer_range": 0.02,
  "bos_token_id": 0,
  "eos_token_id": 0,
  "torch_dtype": "float32",
  "transformers_version": "4.44.0"
}