{ "architectures": [ "GPTModel" ], "model_type": "gpt2", "vocab_size": 50257, "n_positions": 1024, "n_embd": 768, "n_layer": 12, "n_head": 12, "resid_pdrop": 0.1, "activation_function": "gelu_new", "initializer_range": 0.02, "bos_token_id": 50256, "eos_token_id": 50256 }