stanford-futuredata / ColBERT

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

stanford-futuredata/ColBERT Issues

GPU crashes when running "D_packed @ Q.to(dtype=D_packed.dtype).T" with no error message
Updated 14 days ago1
FAILED: decompress_residuals.cuda.o, ninja: build stopped: subcommand failed (from: ColBERT/colbert/indexing/codecs/decompress_residuals.cu)
Closed 6 months ago6
GPU not working while training a new model in Colab
Updated a month ago1
ImportError: cannot import name 'packaging' from 'pkg_resources'
Closed a month ago1
Training script from doc is not working
Updated a month ago
unable to open file </root/.cache/huggingface/hub/models--bert-base-uncased/snapshots/86b5e0934494bd15c9632b12f734a8a67f723594/model.safetensors> in read-only mode: No such file or directory (2)
Closed a month ago
Fine tuning using colbert-ir/colbertv2.0 using training script now gives error
Updated a month ago6
Tokenization Assumption for Query Marker Replacement is Inconsistent
Updated a month ago
Is there a check point of ColBERT that wasn't trained on MSMARCO?
Closed 2 months ago
Add_to_index only work first time
Updated 2 months ago
How to insert new document into the pre-built index?
Updated 2 months ago1
Results on BEIR
Updated 2 months ago
How to get rid of the "Duplicate GPU detected : rank 0 and rank 1 both on CUDA device ca000" error while training of the ColBERTv1.9 modell?
Updated 2 months ago1
Execution fails in colbert.index_objs() with assert classname.endswith('Vector')
Updated 2 months ago
[rank1]:[E ProcessGroupNCCL.cpp:523] [Rank 1] Watchdog caught collective operation timeout: WorkNCCL
Updated 2 months ago2
Extract only embeddings
Updated 2 months ago
How to check the centroids and the data in the clusters?
Updated 2 months ago
ColBert is not failing when Error is encounter during both train and indexing
Updated 3 months ago
How to get the mapping information about doc_id with doc_content.
Updated 3 months ago1
How to quickly check if installation is working fine?
Updated 3 months ago
Request for AMD gpu support
Updated 3 months ago
Where is the qrels.dev.small.tsv?
Updated 4 months ago
CollectionEncoder blocking on encoder N passages
Updated 4 months ago1
type object 'ColBERT' has no attribute 'segmented_maxsim'
Closed 4 months ago1
Focusing retrieval on list of document ids with doc_ids parameter doesn't work
Updated 4 months ago
Tokens in `skiplist` are not returned (masked out) but they still affect other tokens embeddings. Is this expected?
Closed 4 months ago2
How to set chunk_size
Updated 4 months ago
How can I use "all_mpnet_base_v2" model for colbert indexing and searching?
Updated 4 months ago
Basic Training (ColBERTv1-style) -> ujson.JSONDecodeError: Expected object or value
Updated 4 months ago2
crypt.h: No such file or directory
Updated 5 months ago7
Irrelevant results returned by the Colbert V2 Model
Updated 5 months ago1
Duplicate search results when `k` is a high value
Updated 5 months ago8
About training from scratch
Closed 5 months ago8
Pre-filtering the documents based on metadata before late-interaction
Updated 5 months ago5
Issue: Training "resume" and "resume_optimizer" implementation was removed
Updated 5 months ago
What is Colbert v1.9?
Updated 5 months ago
troubleshooting encoding performance
Updated 5 months ago1
Set batch size when indexing
Closed 5 months ago3
Why is the labels initialised to zeros?
Closed 5 months ago1
RuntimeError: quantile() input tensor is too large
Closed 5 months ago4
What does the nway document actually indicate?
Closed 5 months ago1
Parallel indexing operations
Updated 5 months ago
Using with more recent versions of Python than 3.8
Updated 6 months ago3
How to see progress of Indexing
Closed 6 months ago2
How to use a designated GPU for training?
Updated 6 months ago2
FileNotFoundError: [Errno 2] No such file or directory: '***/.venv/lib/python3.8/site-packages/colbert/modeling/segmented_maxsim.cpp'
Closed 6 months ago3
about the ranking operation
Closed 6 months ago1
low recall@1k
Closed 7 months ago2
Using GPU, ColBERT.try_load_torch_extensions from IndexUpdater reports "Error building extension 'segmented_lookup_cpp'"
Updated 7 months ago1
Recall and MRR for checkpoint different from paper
Closed 8 months ago2