Skip to content

Pull requests: stanford-futuredata/ColBERT

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Sort

Pull requests list

Update loaders.py to use r flag for regex
#368 opened Sep 19, 2024 by jimexist Loading…
omit tqdm when pooling embeddings for a single document
#367 opened Sep 17, 2024 by jbellis Loading…
v2.5 training
#361 opened Aug 2, 2024 by bclavie Loading…
Do not do initial retrieval if pids are passed in
#352 opened Jun 11, 2024 by santhnm2 Loading…
Fix tokenization for query marker
#351 opened Jun 10, 2024 by sleep-ee Loading…
Support subclassing of Collection
#330 opened Mar 23, 2024 by jens-ghc Loading…
Building ivf for large datasets
#327 opened Mar 10, 2024 by jenhsia Loading…
Returning passage ID in addition to passage index
#326 opened Mar 10, 2024 by jenhsia Loading…
Example notebook update
#316 opened Mar 4, 2024 by vincent317 Loading…
Allow training with no cuda gpus
#313 opened Feb 27, 2024 by JoshuaPurtell Loading…
added poetry dependency management
#207 opened May 26, 2023 by leo-gan Loading…
Indexing in-memory documents
#196 opened Apr 24, 2023 by fschlatt Loading…
Add new doc to passage splitting mechanism
#187 opened Apr 3, 2023 by VThejas Loading…
Select the device by cuda.is_available
#112 opened Jun 21, 2022 by yuanwu2017 Loading…
[WIP]
#107 opened May 12, 2022 by xm-gui Loading…
export ids during tokenisation
#30 opened Apr 9, 2021 by cmacdonald Loading…
ProTip! no:milestone will show everything without a milestone.