Instructions to use jinaai/xlm-roberta-flash-implementation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jinaai/xlm-roberta-flash-implementation with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jinaai/xlm-roberta-flash-implementation", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Refactor LoRA
#8
by jupyterjazz - opened
No description provided.
jupyterjazz changed pull request status to open
I think it looks good, maybe later we need to adjust it a bit to make it stateless and allow users instead to change the LoRA adapter by passing something to the foward function. Otherwise it might be hard to host it in for the API
jupyterjazz changed pull request status to merged