{ "architectures": [ "GPT2LMHeadModel" ], "model_type": "gpt2", "activation_function": "gelu_new", "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-5, "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_layer": 12, "n_positions": 1024, "resid_pdrop": 0.1, "vocab_size": 50257, "use_cache": true }