aieng-lab/gpt2_commit-intent
014
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 },16 "initializer_range": 0.02,17 "label2id": {18 "LABEL_0": 0,19 "LABEL_1": 1,20 "LABEL_2": 221 },22 "layer_norm_epsilon": 1e-05,23 "model_type": "gpt2",24 "n_ctx": 1024,25 "n_embd": 768,26 "n_head": 12,27 "n_inner": null,28 "n_layer": 12,29 "n_positions": 1024,30 "pad_token_id": 50256,31 "reorder_and_upcast_attn": false,32 "resid_pdrop": 0.1,33 "scale_attn_by_inverse_layer_idx": false,34 "scale_attn_weights": true,35 "summary_activation": null,36 "summary_first_dropout": 0.1,37 "summary_proj_to_labels": true,38 "summary_type": "cls_index",39 "summary_use_proj": true,40 "task_specific_params": {41 "text-generation": {42 "do_sample": true,43 "max_length": 5044 }45 },46 "torch_dtype": "bfloat16",47 "transformers_version": "4.48.3",48 "use_cache": true,49 "vocab_size": 5025750}51 