Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Added Recipe for Multimodal RAG System with Reranking and Quantized Vision Language Model on Consumer GPU #241

Conversation

sergiopaniego
Copy link
Contributor

What does this PR do?

Fixes #240

Who can review?

@merveenoyan and @stevhliu.

Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

Copy link

review-notebook-app bot commented Dec 2, 2024

View / edit / reply to this conversation on ReviewNB

stevhliu commented on 2024-12-02T21:30:20Z
----------------------------------------------------------------

I think this might be a little clearer.

"...by integrating ColQwen2 for document retrieval, MonoQwen2-VL-v0.1 for reranking, and Qwen2-VL as the vision language model (VLM)."


Copy link

review-notebook-app bot commented Dec 2, 2024

View / edit / reply to this conversation on ReviewNB

stevhliu commented on 2024-12-02T21:30:20Z
----------------------------------------------------------------

I think it would be nicer to link to https://huggingface.co/datasets/sergiopaniego/ourworldindata_example so users can preview some of the images they'll be using right from the browser


Copy link

review-notebook-app bot commented Dec 2, 2024

View / edit / reply to this conversation on ReviewNB

stevhliu commented on 2024-12-02T21:30:21Z
----------------------------------------------------------------

Would be helpful to add a sentence explaining what Byaldi is


Copy link
Member

@stevhliu stevhliu left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks, this was super cool to see!

@@ -27,6 +27,7 @@ Check out the recently added notebooks:
- [Multimodal Retrieval-Augmented Generation (RAG) with Document Retrieval (ColPali) and Vision Language Models (VLMs)](multimodal_rag_using_document_retrieval_and_vlms)
- [Fine-Tuning a Vision Language Model (Qwen2-VL-7B) with the Hugging Face Ecosystem (TRL)](fine_tuning_vlm_trl)
- [Multi-agent RAG System 🤖🤝🤖](multiagent_rag_system)
- [Multimodal RAG with ColQwen2, Reranker, and Quantized VLMs on Consumer GPUs](multimodal_rag_using_document_retrieval_and_reranker_and_vlms)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If you don't mind, we could also edit index.md to display only the last 5 recipes to avoid cluttering the main page.

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@sergiopaniego
Copy link
Contributor Author

I've updated the recipe and index.md based on the feedback 😄

@stevhliu stevhliu merged commit a514472 into huggingface:main Dec 3, 2024
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

New Multimodal RAG System with Reranking and Quantized Vision Language Model recipe 🧑‍🍳️
3 participants