aieng-lab/gpt2_comment-type-python

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  },18  "initializer_range": 0.02,19  "label2id": {20    "LABEL_0": 0,21    "LABEL_1": 1,22    "LABEL_2": 2,23    "LABEL_3": 3,24    "LABEL_4": 425  },26  "layer_norm_epsilon": 1e-05,27  "model_type": "gpt2",28  "n_ctx": 1024,29  "n_embd": 768,30  "n_head": 12,31  "n_inner": null,32  "n_layer": 12,33  "n_positions": 1024,34  "pad_token_id": 50256,35  "problem_type": "multi_label_classification",36  "reorder_and_upcast_attn": false,37  "resid_pdrop": 0.1,38  "scale_attn_by_inverse_layer_idx": false,39  "scale_attn_weights": true,40  "summary_activation": null,41  "summary_first_dropout": 0.1,42  "summary_proj_to_labels": true,43  "summary_type": "cls_index",44  "summary_use_proj": true,45  "task_specific_params": {46    "text-generation": {47      "do_sample": true,48      "max_length": 5049    }50  },51  "torch_dtype": "bfloat16",52  "transformers_version": "4.48.3",53  "use_cache": true,54  "vocab_size": 5025755}56