Skip to content

Pull requests: mlfoundations/open_clip

New pull request New
Clear current search query, filters, and sorts
35 Open 328 Closed
35 Open 328 Closed
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
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

enable eval test
#431 opened Feb 15, 2023 by gpucce Loading…
Support distributed evaluation
#176 opened Sep 24, 2022 by mehdidc Loading…
11
add deepspeed zero-stage-1
#264 opened Nov 28, 2022 by Quan-Sun Loading…
2
support layer decay and different lr for text/visual encoder
#268 opened Nov 29, 2022 by Quan-Sun Loading…
20
Matryoshka Representation Learning for Open CLIP
#299 opened Dec 15, 2022 by adityakusupati • Draft
4
Add TextTextCLIP
#323 opened Dec 27, 2022 by lingjzhu Loading…
9 tasks done
21
Support for initializing image tower with pretrained weights
#333 opened Dec 31, 2022 by Ja1Zhou Loading…
Stop trying to guess the length of webdataset datasets
#339 opened Jan 5, 2023 by gabrielilharco Loading…
3
[WIP] Support FSDP
#358 opened Jan 17, 2023 by mehdidc • Draft
23
add audio spectrogram transformer, and full audio clip
#406 opened Feb 3, 2023 by lucidrains Loading…
41
Interpolate positional embeddings for input images with larger sizes
#416 opened Feb 11, 2023 by EeroHeikkinen Loading…
vqa fine tune script
#424 opened Feb 13, 2023 by andrewwangva Loading…
2
Support a sampling strategy for multiple training datasets
#107 opened Jun 9, 2022 by zerovl Loading…
5
Add video support
#430 opened Feb 15, 2023 by iejMac • Draft
11
[WIP] Testing the lion optimizer
#432 opened Feb 16, 2023 by mitchellnw • Draft
39
Experiment using autocast dtype in residual path of text transformer
#433 opened Feb 17, 2023 by rwightman • Draft
Make coca and HF work together
#447 opened Feb 22, 2023 by gpucce • Draft
4 tasks
1
1
Add optional flag in the text model config to return embeddings for all tokens in sequence instead of just the EOS embedding.
#456 opened Mar 2, 2023 by mkaic Loading…
Adding image decoder to CoCa
#467 opened Mar 15, 2023 by iejMac • Draft
4
CoCa: Condition captioning loss on the CLIP similarity
#469 opened Mar 17, 2023 by iejMac • Draft
[WIP] Build open_clip as container and publish on push to main
#485 opened Apr 12, 2023 by Jeadie Loading…
4
Batched CoCa Generation
#498 opened Apr 17, 2023 by sramshetty Loading…
feat: add meta device initialization for pretrained models, 5x faster load times
#501 opened Apr 19, 2023 by ErwannMillon • Draft
5
[WIP] Allow for attention caching during CoCa generation
#502 opened Apr 20, 2023 by sramshetty • Draft
2 tasks
load OpenCLIP model and tokenizer from local path
#883 opened May 21, 2024 by YushunXiang Loading…
ProTip! no:milestone will show everything without a milestone.