config.json

{
    "model_type": "gpt2",
    "vocab_size": 50257,
    "n_positions": 2048,
    "n_ctx": 2048,
    "n_embd": 768,
    "n_layer": 12,
    "n_head": 12,
    "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": 50256,
    "eos_token_id": 50256,
    "pad_token_id": 50256,
    "use_cache": true
}