{
  "architectures": ["GPT2LMHeadModel"],
  "model_type": "gpt2",
  "vocab_size": 50000,
  "n_positions": 2048,
  "n_ctx": 2048,
  "n_embd": 1024,
  "n_layer": 16,
  "n_head": 16,
  "intermediate_size": 3072,
  "activation_function": "gelu_new",
  "resid_pdrop": 0.1,
  "embd_pdrop": 0.1,
  "attn_pdrop": 0.1,
  "layer_norm_epsilon": 1e-5,
  "initializer_range": 0.02,
  "bos_token_id": 0,
  "eos_token_id": 2,
  "pad_token_id": 1,
  "gradient_checkpointing": false,
  "use_cache": true,
  "num_experts": 0
}