aieng-lab/gpt2-xl_comment-type-java
014
1{2 "_name_or_path": "gpt2-xl",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": 1600,34 "n_head": 25,35 "n_inner": null,36 "n_layer": 48,37 "n_positions": 1024,38 "output_past": true,39 "pad_token_id": 50256,40 "problem_type": "multi_label_classification",41 "reorder_and_upcast_attn": false,42 "resid_pdrop": 0.1,43 "scale_attn_by_inverse_layer_idx": false,44 "scale_attn_weights": true,45 "summary_activation": null,46 "summary_first_dropout": 0.1,47 "summary_proj_to_labels": true,48 "summary_type": "cls_index",49 "summary_use_proj": true,50 "task_specific_params": {51 "text-generation": {52 "do_sample": true,53 "max_length": 5054 }55 },56 "torch_dtype": "bfloat16",57 "transformers_version": "4.48.3",58 "use_cache": true,59 "vocab_size": 5025760}61 