Embedding VLMs don't need a head (#45000)

Commit

21 days ago

Embedding VLMs don't need a head (#45000) * squash * fix copies * skip, we dont need to load base model for it * oops, one more regex since now we have no prefix

References

#45000 - Embedding VLMs don't need a head

#45082 - [VidEoMT] Update conversion script

#45110 - Add SAM 3.1

Author

zucchini-nlp

Parents

05514c4b

transformers 4ee7f51e - Embedding VLMs don't need a head (#45000)

transformers
4ee7f51e - Embedding VLMs don't need a head (#45000)