wen1126/github_cybersecurity_READMEs
026
1{2 "_name_or_path": "geralt/MechDistilGPT2",3 "_num_labels": 1,4 "activation_function": "gelu_new",5 "architectures": [6 "GPT2LMHeadModel"7 ],8 "attn_pdrop": 0.1,9 "bos_token_id": 50256,10 "embd_pdrop": 0.1,11 "eos_token_id": 50256,12 "gradient_checkpointing": false,13 "id2label": {14 "0": "LABEL_0"15 },16 "initializer_range": 0.02,17 "label2id": {18 "LABEL_0": 019 },20 "layer_norm_epsilon": 1e-05,21 "model_type": "gpt2",22 "n_ctx": 1024,23 "n_embd": 768,24 "n_head": 12,25 "n_inner": null,26 "n_layer": 6,27 "n_positions": 1024,28 "reorder_and_upcast_attn": false,29 "resid_pdrop": 0.1,30 "scale_attn_by_inverse_layer_idx": false,31 "scale_attn_weights": true,32 "summary_activation": null,33 "summary_first_dropout": 0.1,34 "summary_proj_to_labels": true,35 "summary_type": "cls_index",36 "summary_use_proj": true,37 "task_specific_params": {38 "text-generation": {39 "do_sample": true,40 "max_length": 5041 }42 },43 "torch_dtype": "float32",44 "transformers_version": "4.40.0.dev0",45 "use_cache": true,46 "vocab_size": 5025747}48 