Yuchen Zeng

add one multimodal (text-to-image) in-context learning paper

1

Update paper [**Can MLLMs Perform Text-to-Image In-Context Learning?**](https://arxiv.org/pdf/2402.01293.pdf)

Demo Not Working

1

The Demo of your model is not working anymore. Will it be reactivate again or not?

Quick question: Is there a non-causal optimized form of Flash Linear Attention?

6

Great work! It appears that both GLA and RetNet are optimized only for causal cases. Is there an optimized linear attention for non-causal scenarios?

[Feature] Add support for TRL v0.25.0

1

Thanks so much! Please update the library to support the latest version of TRL (v0.25.0). This will ensure compatibility with new features and improvements introduced in the recent release.

> 1. Did you update? `pip install --upgrade unsloth unsloth_zoo` Yes, updated to the latest version. However, fast_inference=True is still not supported when full_finetuning=True. Please consider implementing this feature —...