{ "_name_or_path": "/persistentshare/storage/team_nakamura/member/yamaguchi/ext_hrk_ymgch_gmail_com/ucllm_nedo_prod/train/output/step3_upload_pretrained_model/gpt_0.084B_wiki-en-ja-2b_65k_no-shuffle_step7751/", "activation_function": "gelu", "architectures": [ "GPT2LMHeadModel" ], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "gradient_checkpointing": false, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": 3072, "n_layer": 8, "n_positions": 2048, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "torch_dtype": "float32", "transformers_version": "4.38.2", "use_cache": true, "vocab_size": 65024 }