Instructions to use strangertoolshf/flash_attention_2_wheelhouse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use strangertoolshf/flash_attention_2_wheelhouse with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("strangertoolshf/flash_attention_2_wheelhouse", dtype="auto") - Notebooks
- Google Colab
- Kaggle
add flash_attention_2 [torch2.4] - initial upload ✅
#1
by prithivMLmods - opened
No description provided.
prithivMLmods changed pull request status to merged