{ "_commit_hash": null, "_name_or_path": "/content/drive/MyDrive/WARNING_PRIVATE_FOLDER/goorm_nlp_8th_group3/goorm_nlp_8th_group3/project3/leadawon/no_commit/best_models/full_24b_3epch", "architectures": [ "EncoderDecoderModel" ], "decoder": { "_name_or_path": "skt/kogpt2-base-v2", "_num_labels": 1, "activation_function": "gelu_new", "add_cross_attention": true, "architectures": [ "GPT2LMHeadModel" ], "attn_pdrop": 0.1, "author": "Heewon Jeon(madjakarta@gmail.com)", "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 0, "chunk_size_feed_forward": 0, "created_date": "2021-04-28", "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "embd_pdrop": 0.1, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 1, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "gradient_checkpointing": false, "id2label": { "0": "LABEL_0" }, "initializer_range": 0.02, "is_decoder": true, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0 }, "layer_norm_epsilon": 1e-05, "length_penalty": 1.0, "license": "CC-BY-NC-SA 4.0", "max_length": 20, "min_length": 0, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 3, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "reorder_and_upcast_attn": false, "repetition_penalty": 1.0, "resid_pdrop": 0.1, "return_dict": true, "return_dict_in_generate": false, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "sep_token_id": null, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "suppress_tokens": null, "task_specific_params": { "text-generation": { "do_sample": true, "max_length": 50 } }, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.25.1", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 51200 }, "decoder_start_token_id": 1, "encoder": { "_name_or_path": "monologg/distilkobert", "activation": "gelu", "add_cross_attention": false, "architectures": [ "DistilBertForMaskedLM" ], "attention_dropout": 0.1, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "dim": 768, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.1, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_dim": 3072, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 512, "min_length": 0, "model_type": "distilbert", "n_heads": 12, "n_layers": 3, "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 1, "prefix": null, "problem_type": null, "pruned_heads": {}, "qa_dropout": 0.1, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": false, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_weights_": true, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.25.1", "typical_p": 1.0, "use_bfloat16": false, "vocab_size": 8002 }, "is_encoder_decoder": true, "model_type": "encoder-decoder", "pad_token_id": 1, "torch_dtype": "float32", "transformers_version": null }