{ "_name_or_path": "gpt2-large", "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, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 1280, "n_head": 20, "n_inner": null, "n_layer": 36, "n_positions": 1024, "output_attentions": true, "pruned_heads": { "2": [ 5 ], "5": [ 4 ], "8": [ 1, 18, 19, 14 ], "9": [ 0, 18, 5, 9, 10, 11 ], "10": [ 1, 18, 17, 19, 15 ], "11": [ 0, 1, 18, 19, 7, 12, 13, 14 ], "12": [ 1, 3, 4, 5, 6, 7, 9, 11, 13, 14, 18 ], "13": [ 1, 4, 5, 6, 7, 14, 15 ], "14": [ 19, 3, 15 ], "15": [ 1, 17, 4, 12, 13 ], "16": [ 0, 2, 6, 9, 15 ], "17": [ 0, 4, 5, 6, 11, 12, 13, 14, 16, 17, 19 ], "18": [ 2, 4, 7, 9, 11, 12, 16, 17, 19 ], "19": [ 1, 2, 4, 6, 8, 11, 12, 13, 15, 17, 18 ], "20": [ 0, 1, 2, 4, 6, 7, 8, 10, 11, 14, 15, 16, 17, 18, 19 ], "21": [ 1, 2, 4, 5, 8, 11, 12, 14, 15, 16, 17, 18, 19 ], "22": [ 0, 2, 3, 4, 5, 6, 7, 8, 10, 12, 13, 14, 16, 18, 19 ], "23": [ 0, 1, 2, 3, 5, 7, 8, 12, 13, 14, 15 ], "24": [ 1, 5, 6, 8, 10, 11, 13, 14, 15, 16, 18, 19 ], "25": [ 0, 1, 3, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 18, 19 ], "26": [ 0, 1, 2, 3, 4, 6, 8, 9, 10, 12, 13, 14, 15, 16, 17 ], "27": [ 0, 1, 2, 4, 6, 7, 9, 10, 12, 13, 14, 16, 17, 18 ], "28": [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 13, 14, 16, 17, 18, 19 ], "29": [ 0, 1, 2, 3, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19 ], "30": [ 0, 1, 2, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19 ], "31": [ 0, 1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19 ], "32": [ 0, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19 ], "33": [ 0, 1, 2, 3, 4, 5, 6, 7, 9, 10, 12, 13, 14, 15, 17, 18, 19 ], "34": [ 0, 1, 3, 5, 7, 9, 12, 13, 14, 16, 17, 18, 19 ], "35": [ 1 ] }, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "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": { "text-generation": { "do_sample": true, "max_length": 50 } }, "torch_dtype": "float32", "transformers_version": "4.36.2", "use_cache": true, "vocab_size": 50257 }