{ "afn": "gelu", "architectures": [ "OpenAIGPTLMHeadModel" ], "attn_pdrop": 0.1, "embd_pdrop": 0.1, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "openai-gpt", "n_ctx": 512, "n_embd": 768, "n_head": 12, "n_layer": 12, "n_positions": 512, "n_special": 0, "predict_special_tokens": true, "resid_pdrop": 0.1, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": { "text-generation": { "do_sample": true, "max_length": 50 } }, "vocab_size": 40478 }