Blog alert: check out the new guest post by Amog Kamsetty and the @raydistributed team on training a Retrieval Augmented Generation Model with Hugging Face and Ray!
huggingface.co/blog/ray-rag
huggingface.co/blog/ray-rag
The RAG model by @olapiktus @PSH_Lewis and @facebookai colleagues leverages external knowledge sources like Wikipedia to have direct and dynamic access to information at inference time
Part of this process relies on training a retriever to learn how to find that information
Part of this process relies on training a retriever to learn how to find that information
@raydistributed is a framework-agnostic, flexible implementation for ad-hoc concurrent programming, which makes it ideal for scaling up this training, making retrieval 2x faster and drastically improving the scalability of RAG distributed fine-tuning
Go try it out for yourself!
Go try it out for yourself!
And check out all of the relevant resources in:
RAGxRay Post: huggingface.co/blog/ray-rag
HF model page: huggingface.co/transformers/m…
Ray documentation: docs.ray.io/en/master/
RAG paper: arxiv.org/abs/2005.11401
RAG demo: huggingface.co/rag/
RAGxRay Post: huggingface.co/blog/ray-rag
HF model page: huggingface.co/transformers/m…
Ray documentation: docs.ray.io/en/master/
RAG paper: arxiv.org/abs/2005.11401
RAG demo: huggingface.co/rag/
• • •
Missing some Tweet in this thread? You can try to
force a refresh
