I’m interested in NLP, specifically LLMs and representation techniques. You may know me from my frequent twitter rants about using late-interaction over dense vectors.
I’m building 🪤RAGatouille, a python library whose grand aim is to bridge the gap between state-of-the-art research code and commonly used practices.
Right now, RAGatouille aims to allow you to seamlessly train and use ColBERT models to support RAG applications.
Recently, I’ve also made the 👔 state-of-the-art job skills detection approach (@BrightNetwork), 🇯🇵 JaColbert, the (current) strongest document retrieval model in Japanese.
I’m very interested in collaborating with companies seeking to improve their LLM/Retrieval practices, or even seeking to improve LLM/Retrieval practices as whole!
Feel free to reach out if you’d like to talk ML or explore working together.