Andcircle
Andcircle
@sgugger Sorry another question here =) as above
> hi @Andcircle Do you face the same issue with the `main` branch of transformers? > > ``` > pip install -U git+https://github.com/huggingface/transformers.git > ``` Hi @younesbelkada, Once I changed...
> Follow-up TODO: Support initializing VLM with only language model backbone. @ywang96 @DarkLight1337 Thanks for the update! I checked the demo code, we still provide 2 modality separately, prompt and...
@ywang96 Thanks for your fast response! Yes, I think #6869 should free us. Just to be clarified, #6869 's use case can be much broader =) not only for embedding...
> > @ywang96 Thanks for your fast response! Yes, I think #6869 should free us. > > Just to be clarified, #6869 's use case can be much broader =)...
@ywang96 Will have a look, thank =)
@ywang96 It would be great to support fuyu style. But if we can somehow let user provide embedding themselves like pseudo code above, the embedding is already decoupled from tokenizer,...
any updates on this problem?
@markrmiller I'm facing the same issue with paged_adamw_8bit, did you find any solution for it? thanks 🙏
@markrmiller thanks for advice