| { | |
| "_name_or_path": "/opt/ml/kobigbirdbart_tapt_ep3_bs16_pre_RD", | |
| "architectures": [ | |
| "EncoderDecoderModel" | |
| ], | |
| "decoder": { | |
| "_name_or_path": "gogamza/kobart-base-v1", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "add_bias_logits": false, | |
| "add_cross_attention": true, | |
| "add_final_layer_norm": false, | |
| "architectures": [ | |
| "BartModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "author": "Heewon Jeon(madjakarta@gmail.com)", | |
| "bad_words_ids": null, | |
| "bos_token_id": 0, | |
| "chunk_size_feed_forward": 0, | |
| "classif_dropout": 0.1, | |
| "classifier_dropout": 0.1, | |
| "d_model": 768, | |
| "decoder_attention_heads": 16, | |
| "decoder_ffn_dim": 3072, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 6, | |
| "decoder_start_token_id": 1, | |
| "diversity_penalty": 0.0, | |
| "do_blenderbot_90_layernorm": false, | |
| "do_sample": false, | |
| "doc_type_size": 4, | |
| "dropout": 0.1, | |
| "early_stopping": false, | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 3072, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 6, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 1, | |
| "extra_pos_embeddings": 2, | |
| "finetuning_task": null, | |
| "force_bos_token_to_be_generated": false, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": 1, | |
| "gradient_checkpointing": false, | |
| "id2label": { | |
| "0": "NEGATIVE", | |
| "1": "POSITIVE" | |
| }, | |
| "init_std": 0.02, | |
| "is_decoder": true, | |
| "is_encoder_decoder": true, | |
| "kobart_version": 1.0, | |
| "label2id": { | |
| "NEGATIVE": 0, | |
| "POSITIVE": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 2048, | |
| "min_length": 0, | |
| "model_type": "bart", | |
| "no_repeat_ngram_size": 0, | |
| "normalize_before": false, | |
| "normalize_embedding": true, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 6, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 0, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "scale_embedding": false, | |
| "sep_token_id": null, | |
| "static_position_embeddings": false, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": "PreTrainedTokenizerFast", | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "transformers_version": "4.11.0", | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 32500 | |
| }, | |
| "encoder": { | |
| "_name_or_path": "monologg/kobigbird-bert-base", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "BigBirdForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "attention_type": "block_sparse", | |
| "bad_words_ids": null, | |
| "block_size": 64, | |
| "bos_token_id": 5, | |
| "chunk_size_feed_forward": 0, | |
| "classifier_dropout": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "doc_type_size": 4, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 6, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu_new", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 4096, | |
| "min_length": 0, | |
| "model_type": "big_bird", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 12, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 6, | |
| "num_random_blocks": 3, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "rescale_embeddings": false, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": 3, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "float32", | |
| "torchscript": false, | |
| "transformers_version": "4.11.0", | |
| "type_vocab_size": 2, | |
| "use_bfloat16": false, | |
| "use_bias": true, | |
| "use_cache": true, | |
| "vocab_size": 32500 | |
| }, | |
| "is_encoder_decoder": true, | |
| "model_type": "encoder-decoder", | |
| "torch_dtype": "float32", | |
| "transformers_version": null | |
| } | |