Pull Requests mlfoundations/open_clip

NaFlex + audio

#1170 opened 2026-06-02 18:00 by rwightman

NaFlexGenLIP experiment

#1168 opened 2026-06-01 18:09 by rwightman

Try out TIPSV2 in image-text mode, zero-shot seems to work

#1166 opened 2026-05-27 18:04 by rwightman

Support loading a model in a non-init-weights context

#1105 opened 2025-08-06 18:36 by bryant1410

[WIP] Add mammut

#641 opened 2023-09-19 11:49 by gpucce

Save intermediate checkpoints when sampling without replacement (take 2)

#535 opened 2023-05-17 16:04 by gabrielilharco

[WIP] Allow for attention caching during CoCa generation

#502 opened 2023-04-20 04:23 by sramshetty

feat: add meta device initialization for pretrained models, 5x faster load times

#501 opened 2023-04-19 21:00 by ErwannMillon

Batched CoCa Generation

#498 opened 2023-04-17 04:00 by sramshetty

Make coca and HF work together

#447 opened 2023-02-22 18:34 by gpucce

Add video support

#430 opened 2023-02-15 11:11 by iejMac

Interpolate positional embeddings for input images with larger sizes

#416 opened 2023-02-11 16:22 by EeroHeikkinen

Stop trying to guess the length of webdataset datasets

#339 opened 2023-01-05 15:23 by gabrielilharco

Add TextTextCLIP

#323 opened 2022-12-27 22:09 by lingjzhu

support layer decay and different lr for text/visual encoder

#268 opened 2022-11-29 07:36 by Quan-Sun

Support distributed evaluation

#176 opened 2022-09-24 17:11 by mehdidc

Added ability to load pre-computed vectors from Pickle file

#134 opened 2022-07-27 20:52 by taylor-brown

Support a sampling strategy for multiple training datasets

#107 opened 2022-06-09 07:18 by zerovl