{ "activation_function": "gelu_new", "add_cross_attention": false, "architectures": [ "GPT2ForSequenceClassification" ], "attn_pdrop": 0.0, "bos_token_id": 12, "dtype": "float32", "embd_pdrop": 0.0, "eos_token_id": 13, "id2label": { "0": "false", "1": "true" }, "initializer_range": 0.02, "label2id": { "false": 0, "true": 1 }, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 256, "n_embd": 64, "n_head": 4, "n_inner": null, "n_layer": 4, "n_positions": 256, "pad_token_id": 16, "problem_type": "single_label_classification", "reorder_and_upcast_attn": false, "resid_pdrop": 0.0, "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, "tie_word_embeddings": true, "transformers_version": "5.8.0", "use_cache": false, "vocab_size": 17 }