1 2 9

Pierre-Louis B PRO

PLB

AI & ML interests

None yet

Recent Activity

Reacted to thomwolf's post with 🤯 15 days ago

Very exciting new https://huggingface.co/mistralai/Pixtral-Large-Instruct-2411 model from Mistral-AI Impressive performances, huge congrats @patrickvonplaten @sgvaze @pandora-s @devendrachaplot @sophiamyang and team! Very nice to have SOTA Multilingual OCR and Chart understanding in an open-weights model

replied to their post 17 days ago

⚠️ People selling AI chatbots for websites hate us. Add an open source chat assistant on your website in 5 minutes: https://github.com/phospho-app/ai-chat-bubble How does it work ? - You give an URL - The AI assistant crawls the website content and embed it - Add it to your frontend in one line of code - People on your website can ask the assistant questions Powered by https://huggingface.co/BAAI/bge-small-en-v1.5 and Mistral AI

posted an update 20 days ago

View all activity

Articles

EmbeddingAlign RAG: Boosting QA Systems

Oct 18

• 12

Organizations

PLB's activity

reacted to thomwolf's post with 🤯 15 days ago

Post

1395

Very exciting new mistralai/Pixtral-Large-Instruct-2411 model from Mistral-AI

Impressive performances, huge congrats @patrickvonplaten @sgvaze @pandora-s @devendrachaplot @sophiamyang and team!

Very nice to have SOTA Multilingual OCR and Chart understanding in an open-weights model

replied to their post 17 days ago

We didn't deploy a live version yet. Will ping you when we do so!

posted an update 20 days ago

Post

1849

⚠️ People selling AI chatbots for websites hate us.
Add an open source chat assistant on your website in 5 minutes: https://github.com/phospho-app/ai-chat-bubble

How does it work ?
- You give an URL
- The AI assistant crawls the website content and embed it
- Add it to your frontend in one line of code
- People on your website can ask the assistant questions

Powered by BAAI/bge-small-en-v1.5 and Mistral AI

5 replies

upvoted an article 29 days ago

Article

Recipe: Preparing Multilingual Speech Datasets for TTS Training

•

30 days ago

• 14

replied to their post about 2 months ago

As always, there is a trade-off to find between generality and absolute performance. If you have multiple different domaines/dataset with a clear separation, I think it would make sens to train an adapter for each domain.

posted an update about 2 months ago

Post

368

📈 Increase the quality of your RAG with a simple Linear Layer! No need to change your embedding model (keep that old OpenAI API).

Introducing EmbeddingAlign RAG, a novel approach to improve Retrieval-Augmented Generation (RAG) systems.

Key highlights:
- Uses a simple linear transformation on existing embeddings
- Boosts hit rate from 89% to 95% on real-world examples
- Minor increase on latency (less than 10ms)
- Works on top of blackbox embedding models (Mistral AI, OpenAI, Cohere,...)
- No dataset needed (just your documents)
- Train easily on CPU

🤗 Read the full article here on HF: https://huggingface.co/blog/PLB/embedding-align-rag