Transformers
PyTorch
t5
generative-retrieval
information-retrieval
msmarco
robustness
reproducibility
text-generation-inference
Instructions to use kiyam/lost-in-decoding-pag with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kiyam/lost-in-decoding-pag with Transformers:
# Load model directly from transformers import AutoTokenizer, T5ForLexicalSemanticGeneration tokenizer = AutoTokenizer.from_pretrained("kiyam/lost-in-decoding-pag") model = T5ForLexicalSemanticGeneration.from_pretrained("kiyam/lost-in-decoding-pag", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_name_or_path": "t5-base", | |
| "num_decoder_layers": null, | |
| "teacher_score_path": "\/home\/ec2-user\/quic-efs\/user\/hansizeng\/work\/term_generative_retriever\/experiments-full-lexical-ripor\/t5-full-dense-1-5e-4-12l\/out\/MSMARCO_TRAIN\/qrel_added_merged_teacher_scores.json", | |
| "collection_path": "\/home\/ec2-user\/quic-efs\/user\/hansizeng\/work\/data\/msmarco-full\/full_collection\/", | |
| "queries_path": "\/home\/ec2-user\/quic-efs\/user\/hansizeng\/work\/data\/msmarco-full\/all_train_queries\/train_queries", | |
| "qrels_path": "\/home\/ec2-user\/quic-efs\/user\/hansizeng\/work\/data\/msmarco\/train_queries\/qrels.json", | |
| "output_dir": "\/home\/ec2-user\/quic-efs\/user\/hansizeng\/work\/term_generative_retriever\/experiments-full-lexical-ripor\/lexical_ripor_direct_lng_knp_seq2seq_1\/checkpoint", | |
| "example_path": null, | |
| "pseudo_queries_to_docid_path": null, | |
| "pseudo_queries_to_mul_docid_path": null, | |
| "docid_to_smtid_path": "", | |
| "docid_to_tokenids_path": null, | |
| "qid_to_smtid_path": null, | |
| "first_centroid_path": null, | |
| "second_centroid_path": null, | |
| "third_centroid_path": null, | |
| "qid_to_rrpids_path": null, | |
| "docid_decode_eval_path": null, | |
| "centroid_path": null, | |
| "centroid_idx": null, | |
| "triple_margin_mse_path": null, | |
| "query_to_docid_path": null, | |
| "teacher_rerank_nway_path": null, | |
| "bce_example_path": null, | |
| "smt_docid_to_smtid_path": "\/home\/ec2-user\/quic-efs\/user\/hansizeng\/work\/term_generative_retriever\/experiments-full-lexical-ripor\/t5-full-dense-1-5e-4-12l\/aq_smtid\/docid_to_tokenids.json", | |
| "lex_docid_to_smtid_path": "\/home\/ec2-user\/quic-efs\/user\/hansizeng\/work\/term_generative_retriever\/experiments-splade\/t5-splade-0-12l\/\/top_bow\/docid_to_tokenids.json", | |
| "run_name": "lexical_ripor_direct_lng_knp_seq2seq_1", | |
| "pretrained_path": "\/home\/ec2-user\/quic-efs\/user\/hansizeng\/work\/term_generative_retriever\/experiments-full-lexical-ripor\/ripor_direct_lng_knp_seq2seq_1\/checkpoint\/", | |
| "loss_type": "direct_lng_knp_margin_mse", | |
| "model_type": "lexical_ripor", | |
| "do_eval": false, | |
| "max_length": 64, | |
| "learning_rate": 0.0005, | |
| "warmup_ratio": 0.04, | |
| "per_device_train_batch_size": 64, | |
| "logging_steps": 50, | |
| "max_steps": -1, | |
| "epochs": 120, | |
| "local_rank": 0, | |
| "task_names": [ | |
| "rank_4", | |
| "rank", | |
| "lexical_rank" | |
| ], | |
| "ln_to_weight": { | |
| "rank_4": 1.0, | |
| "rank": 1.0, | |
| "lexical_rank": 1.0 | |
| }, | |
| "multi_weights": null, | |
| "nway_label_type": null, | |
| "nway_rrpids": 24, | |
| "nway": 12, | |
| "eval_steps": 50, | |
| "use_fp16": true, | |
| "multi_vocab_sizes": false, | |
| "save_steps": 15000, | |
| "wandb_project_name": "full_lexical_ripor", | |
| "pad_token_id": null, | |
| "smtid_as_docid": false, | |
| "apply_lex_loss": false, | |
| "eval_collection_path": null, | |
| "eval_queries_path": null, | |
| "full_rank_eval_qrel_path": null, | |
| "full_rank_eval_topk": 200, | |
| "full_rank_index_dir": null, | |
| "full_rank_out_dir": null | |
| } |