hckhck/buda_learning

1{2  "_name_or_path": "skt/kogpt2-base-v2",3  "_num_labels": 1,4  "activation_function": "gelu_new",5  "architectures": [6    "GPT2LMHeadModel"7  ],8  "attn_pdrop": 0.1,9  "author": "Heewon Jeon(madjakarta@gmail.com)",10  "bos_token_id": 0,11  "created_date": "2021-04-28",12  "embd_pdrop": 0.1,13  "eos_token_id": 1,14  "gradient_checkpointing": false,15  "id2label": {16    "0": "LABEL_0"17  },18  "initializer_range": 0.02,19  "label2id": {20    "LABEL_0": 021  },22  "layer_norm_epsilon": 1e-05,23  "license": "CC-BY-NC-SA 4.0",24  "model_type": "gpt2",25  "n_ctx": 1024,26  "n_embd": 768,27  "n_head": 12,28  "n_inner": null,29  "n_layer": 12,30  "n_positions": 1024,31  "pad_token_id": 3,32  "reorder_and_upcast_attn": false,33  "resid_pdrop": 0.1,34  "scale_attn_by_inverse_layer_idx": false,35  "scale_attn_weights": true,36  "summary_activation": null,37  "summary_first_dropout": 0.1,38  "summary_proj_to_labels": true,39  "summary_type": "cls_index",40  "summary_use_proj": true,41  "task_specific_params": {42    "text-generation": {43      "do_sample": true,44      "max_length": 5045    }46  },47  "torch_dtype": "float32",48  "transformers_version": "4.19.4",49  "use_cache": true,50  "vocab_size": 5120051}52