{ "_name_or_path": "gpt2", "activation_function": "gelu_new", "architectures": [ "GPT2ForTokenClassification" ], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "id2label": { "0": "O", "1": "B-corporation", "2": "I-corporation", "3": "B-creative-work", "4": "I-creative-work", "5": "B-group", "6": "I-group", "7": "B-location", "8": "I-location", "9": "B-person", "10": "I-person", "11": "B-product", "12": "I-product" }, "initializer_range": 0.02, "label2id": { "B-corporation": 1, "B-creative-work": 3, "B-group": 5, "B-location": 7, "B-person": 9, "B-product": 11, "I-corporation": 2, "I-creative-work": 4, "I-group": 6, "I-location": 8, "I-person": 10, "I-product": 12, "O": 0 }, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "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": "4.31.0", "use_cache": true, "vocab_size": 50257 }