Hi there, I’m Ben 👋

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.

Questions & Answer(s): thoughts and joining Answer.AI

If you’re old school, you can find a raw HTML version of this post here This is a fairly long, stream-of-thought post about how I currently (Sunday Feb 4, 2024) feel about the broader ML/NLP/IR ecosystem and its future. Everything here’s on-the-fly opinion and can & will change. In summary: I think ML developments are incredibly exciting, and we need to continue to work on bridging the gap between ML-as-a-commodity-for-ML-practitioners to ML-as-a-commodity-for-everyone....

Fio

日本語版は近日公開予定です（日本語を勉強中なので、間違いはご容赦ください！） Welcome to this stream-of-thoughts report on fio-base-japanese-v0.1, the first version of Fio, a family of Japanese sentence embeddings. These are all notes I took while training the models, vaguely ordered in relevant categories! I hope that they can be useful to anyone interested in Japanese embeddings. In short: Fio-v0.1 is currently (18/12/2023) the best similarity sentence embeddings model for Japanese, as well as the best overall monolingual model (similarity + retrieval)....