aieng-lab/gpt2_comment-type-java

1{2  "_name_or_path": "gpt2",3  "activation_function": "gelu_new",4  "architectures": [5    "GPT2ForSequenceClassification"6  ],7  "attn_pdrop": 0.1,8  "bos_token_id": 50256,9  "embd_pdrop": 0.1,10  "eos_token_id": 50256,11  "id2label": {12    "0": "LABEL_0",13    "1": "LABEL_1",14    "2": "LABEL_2",15    "3": "LABEL_3",16    "4": "LABEL_4",17    "5": "LABEL_5",18    "6": "LABEL_6"19  },20  "initializer_range": 0.02,21  "label2id": {22    "LABEL_0": 0,23    "LABEL_1": 1,24    "LABEL_2": 2,25    "LABEL_3": 3,26    "LABEL_4": 4,27    "LABEL_5": 5,28    "LABEL_6": 629  },30  "layer_norm_epsilon": 1e-05,31  "model_type": "gpt2",32  "n_ctx": 1024,33  "n_embd": 768,34  "n_head": 12,35  "n_inner": null,36  "n_layer": 12,37  "n_positions": 1024,38  "pad_token_id": 50256,39  "problem_type": "multi_label_classification",40  "reorder_and_upcast_attn": false,41  "resid_pdrop": 0.1,42  "scale_attn_by_inverse_layer_idx": false,43  "scale_attn_weights": true,44  "summary_activation": null,45  "summary_first_dropout": 0.1,46  "summary_proj_to_labels": true,47  "summary_type": "cls_index",48  "summary_use_proj": true,49  "task_specific_params": {50    "text-generation": {51      "do_sample": true,52      "max_length": 5053    }54  },55  "torch_dtype": "bfloat16",56  "transformers_version": "4.48.3",57  "use_cache": true,58  "vocab_size": 5025759}60