Apply for community grant: Personal project (gpu)

#2
by chansung - opened

This project shows how you can build complex chatting program with Open Source LLM (LLaMA2).

The chatting itself works with Hugging Face Inference API with my PRO subscription, so I don't need GPU for that. However, this project also shows how to integrate Open Source embedding model (e5-large-v2) + Open Source vector database (ChromaDB) to enable Internet search capabilities.

In order to handle generating embeddings from searched results, default hardware spec is not enough, but T4 instance should be sufficient. Since this space is featured in "Spaces of the week", I thought I could apply for a community grant for that.

Hi @chansung , we have assigned a gpu to this space. Note that GPU Grants are provided temporarily and might be removed after some time if the usage is very low.

To learn more about GPUs in Spaces, please check out https://huggingface.co/docs/hub/spaces-gpus

@hysts

thank you so much!

chansung changed discussion status to closed

Sign up or log in to comment