Merged
Conversation
…for limiting loaded items
…h of different models
…same device as the module
- Updated BruteForceSearcher to use register_buffer for kb_embs and added eval mode with gradient disabling. - Modified DPBruteForceSearcherPT to compile the searcher and improve inference performance. - Enhanced create_binary_dataset to sort embeddings and qids, and adjusted data types for better memory efficiency. - Refactored PairwiseMLPReranker to streamline the forward pass and ensure base model remains non-trainable. - Introduced validation during training in the trainer module and improved logging for better monitoring. - Added a new reranking2 script for improved entity linking functionality. - Removed deprecated reranking.py script to clean up the codebase. - Updated test cases for pairwise MLP and training configurations to reflect recent changes.
…nk token loading and dataset creation logic
- Updated `trainer.py` to support dynamic configuration loading and improved logging with Weights & Biases integration. - Introduced `trainer_simple.py` for simplified single-device training. - Enhanced `training_configs.py` with additional model configurations and parameters. - Modified `reranking2.py` and added `reranking3.py` for improved reranking functionality and model evaluation. - Implemented a new test suite for `PairwiseMLPRerankerWithRetrievalScore` and `RerankingIterableDataset`. - Added support for new models including `FullLEALLAReranker` and `PairwiseMLPRerankerWithLargeContextEmb`. - Improved data handling and validation logic in training scripts.
…_from_tokens_model_name_and_state_dict
- Implemented `map_qids_to_token_matrix` function in `loaders.py` to create a sparse matrix mapping qids to their token vectors. - Added unit tests for `map_qids_to_token_matrix` in `test_loaders.py` to verify correct mapping and handling of non-existent qids. - Created a new test file `test_change_dataset_tokens.py` to test the `update_tokens_in_file` and `process_directory` functions. - Updated `uv.lock` to include `scipy` as a dependency.
…rt and parallel processing
…able dataset for training
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.