| { | |
| "architectures": [ | |
| "RagSequenceForGeneration" | |
| ], | |
| "dataset": "wiki_dpr", | |
| "dataset_split": "train", | |
| "do_deduplication": true, | |
| "do_marginalize": false, | |
| "doc_sep": " // ", | |
| "exclude_bos_score": false, | |
| "forced_eos_token_id": 2, | |
| "generator": { | |
| "_name_or_path": "zhiweitong/bart-large-nq-qg", | |
| "activation_dropout": 0.1, | |
| "activation_function": "gelu", | |
| "add_bias_logits": false, | |
| "add_cross_attention": false, | |
| "add_final_layer_norm": false, | |
| "architectures": [ | |
| "BartForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bad_words_ids": null, | |
| "bos_token_id": 0, | |
| "chunk_size_feed_forward": 0, | |
| "classif_dropout": 0.1, | |
| "classifier_dropout": 0.0, | |
| "cross_attention_hidden_size": null, | |
| "d_model": 1024, | |
| "decoder_attention_heads": 16, | |
| "decoder_ffn_dim": 4096, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 12, | |
| "decoder_start_token_id": 2, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dropout": 0.1, | |
| "early_stopping": true, | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 4096, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 12, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 2, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": 0, | |
| "forced_eos_token_id": 2, | |
| "gradient_checkpointing": false, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2" | |
| }, | |
| "init_std": 0.02, | |
| "is_decoder": false, | |
| "is_encoder_decoder": true, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 1024, | |
| "min_length": 0, | |
| "model_type": "bart", | |
| "no_repeat_ngram_size": 3, | |
| "normalize_before": false, | |
| "num_beam_groups": 1, | |
| "num_beams": 4, | |
| "num_hidden_layers": 12, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 1, | |
| "prefix": " ", | |
| "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, | |
| "task_specific_params": { | |
| "summarization": { | |
| "length_penalty": 1.0, | |
| "max_length": 128, | |
| "min_length": 12, | |
| "num_beams": 4 | |
| }, | |
| "summarization_cnn": { | |
| "length_penalty": 2.0, | |
| "max_length": 142, | |
| "min_length": 56, | |
| "num_beams": 4 | |
| }, | |
| "summarization_xsum": { | |
| "length_penalty": 1.0, | |
| "max_length": 62, | |
| "min_length": 11, | |
| "num_beams": 6 | |
| } | |
| }, | |
| "temperature": 1.0, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "float32", | |
| "torchscript": false, | |
| "transformers_version": "4.15.0", | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 50266 | |
| }, | |
| "index_name": "legacy", | |
| "index_path": null, | |
| "is_encoder_decoder": true, | |
| "label_smoothing": 0.0, | |
| "max_combined_length": 300, | |
| "model_type": "rag", | |
| "n_docs": 5, | |
| "output_retrieved": false, | |
| "passages_path": null, | |
| "prefix": null, | |
| "question_encoder": { | |
| "_name_or_path": "zhiweitong/dpr-answer_encoder-single-nq-base", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "DPRQuestionEncoder" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bad_words_ids": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "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": 512, | |
| "min_length": 0, | |
| "model_type": "dpr", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 12, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 12, | |
| "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, | |
| "projection_dim": 0, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "float32", | |
| "torchscript": false, | |
| "transformers_version": "4.15.0", | |
| "type_vocab_size": 2, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 30522 | |
| }, | |
| "reduce_loss": false, | |
| "retrieval_batch_size": 8, | |
| "retrieval_vector_size": 768, | |
| "title_sep": " / ", | |
| "torch_dtype": "float32", | |
| "transformers_version": null, | |
| "use_cache": true, | |
| "use_dummy_dataset": false, | |
| "vocab_size": null | |
| } | |