This category should be used to propose and join existing projects that make use of Flax/JAX and Transformers. Make sure that your project proposal includes all relevant information (as listed below) for people to join/comment/improve your idea.
Relevant information when proposing a / project:
- Description: What is the project about? E.g. Train a CLIP model in Swedish for zero-shot image classification.
- Model: What model do you propose to use? E.g. openai/clip-vit-base-patch32 · Hugging Face in Flax/JAX
- Dataset: What dataset do you want to use? E.g. GitHub - google-research-datasets/wit: WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.
- Training scripts: What training scripts do you want to use? E.g. Training scripts will be created as part of the project
- Expected result: What do you expect the outcome of the project to be? E.g. A zero-shot image classification pipeline for CLIP