Repository Issue Activity (beta)

#411 📋 Documentation Enhancement Suggestion

#408 Proposal: Integrate Flash-KMeans for significantly faster and more memory-efficient clustering

#410 Reproduce colbert-v2 results

#407 Deleting the first element in index (pids[0]) - Error: List index out of range

#392 can search passage text by pid ?

#376 Generalized Thresholding for ColBERT Scores Across Datasets

#360 ValueError: negative shift count

#394 Highlight relevant passages in document

#389 Prebuilt index for wikipedia?

#384 Colbert v2 retrieval model cannot perform top p retrieval recall

#403 Incorrect Data Selected with Multi-NODE DDP Training

#406 Clarity on Training/Evaluation Details to Replicate models in Colbert v1 and Colbert v2 papers

#404 Entire Triplets Data loaded into Memory

#7 trying distributed multigpu

#396 FAISS GPU usage with pip

#356 ImportError: .../torch_extensions/py38_cu117/decompress_residuals_cpp/decompress_residuals_cpp.so: cannot open shared object file: No such file or directory

#371 ninja: build stopped: subcommand failed.

#391 transformers.AdamW has been removed

#399 Bug: Incorrect `git-python` dependency in PyPI releases

#374 Normalizing the Final Similarity Score to reduce it between 0 and 1

#397 ImportError: cannot import name 'AdamW' from 'transformers'

#398 AttributeError: 'CollectionIndexer' object has no attribute 'num_sample_embs'

#383 Additional Steps needed for the Pip Install in Google Colab

#315 How can I use "all_mpnet_base_v2" model for colbert indexing and searching?

#177 Is it possible to add metadata filtering logic to ColBERTv2?