attn_implementation
#3
by
don412
- opened
Does the "rhymes-ai/Aria" model support "eager" for "attn_implementation", it doesn't seem so.
With or without this parameter and the "eager" value, I get the following error:
ValueError: AriaVisionModel does not support Flash Attention 2.0 yet. Please request to add support where the model is hosted, on its model hub page: https://huggingface.co//discussions/new or in the Transformers GitHub repo: https://github.com/huggingface/transformers/issues/new
fyi, my transformers version is 4.41.0, and I cannot upgrade to a newer one because existing tools depend on it.