{ "activation_function": "gelu_new", "architectures": [ "GPT2LMHeadModel" ], "attn_pdrop": 0.1, "author": "Heewon Jeon(madjakarta@gmail.com)", "bos_token_id": 0, "created_date": "2021-04-28", "embd_pdrop": 0.1, "eos_token_id": 1, "gradient_checkpointing": false, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "license": "CC-BY-NC-SA 4.0", "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "pad_token_id": 3, "resid_pdrop": 0.1, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": { "conversational": { "max_length": 1000 } }, "transformers_version": "4.8.1", "use_cache": true, "vocab_size": 51200 }