{ "_name_or_path": "gpt2", "activation_function": "gelu_new", "architectures": [ "GPT2ForSequenceClassification" ], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "id2label": { "0": "change_request", "1": "discussion_participation", "2": "discussion_trigger", "3": "acknowledgement", "4": "reference", "5": "critical" }, "initializer_range": 0.02, "label2id": { "acknowledgement": 3, "change_request": 0, "critical": 5, "discussion_participation": 1, "discussion_trigger": 2, "reference": 4 }, "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, "pad_token_id": 15, "problem_type": "single_label_classification", "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 }