MarkProMaster229/InternetLanguage

1{2  "activation_function": "gelu_new",3  "architectures": [4    "GPT2LMHeadModel"5  ],6  "attn_pdrop": 0.1,7  "bos_token_id": 1,8  "dtype": "float32",9  "embd_pdrop": 0.1,10  "eos_token_id": 2,11  "gradient_checkpointing": false,12  "id2label": {13    "0": "LABEL_0"14  },15  "initializer_range": 0.02,16  "label2id": {17    "LABEL_0": 018  },19  "layer_norm_epsilon": 1e-05,20  "model_type": "gpt2",21  "n_ctx": 2048,22  "n_embd": 768,23  "n_head": 12,24  "n_inner": null,25  "n_layer": 12,26  "n_positions": 2048,27  "pad_token_id": 2,28  "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  "transformers_version": "4.57.3",38  "use_cache": true,39  "vocab_size": 5025740}41