{
  "activation_function": "gelu",
  "architecture": "gpt2",
  "architectures": [
    "GPT2LMHeadModel"
  ],
  "attn_pdrop": 0.0,
  "block_type": "gpt2_prelayernorm",
  "causal_mask_mode": "buffered_upper_triangular",
  "embd_pdrop": 0.0,
  "init_strategy": "gpt2_std_0.02_residual_scale",
  "layer_norm_epsilon": 1e-05,
  "model_type": "gpt2",
  "n_ctx": 2500,
  "n_embd": 1024,
  "n_head": 16,
  "n_layer": 24,
  "n_positions": 2500,
  "norm_order": "preln",
  "norm_type": "layernorm",
  "positional_encoding": "learned_absolute",
  "resid_pdrop": 0.0,
  "tie_word_embeddings": true,
  "use_cache": true,
  "vocab_size": 32000
}