{ "activation_function": "gelu_new", "architectures": [ "GPT2LMHeadModel" ], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "max_position_embeddings": 4096, "model_type": "gpt2", "n_ctx": 4096, "n_embd": 1024, "n_inner": 4096, "n_head": 16, "n_layer": 32, "n_positions": 4096, "resid_pdrop": 0.1, "vocab_size": 50257 }