Maxence Lasbordes

PhD Student @LightOnIO | Post-Training

[Maxence Lasbordes @maxencelsb]

🚀 Introducing ColGrep-Agent-2B!

An open 2B model, now integrated into NextPlaid via ColGrep, that runs locally to make coding agents more efficient.

With Claude Code:

→ 34% fewer API tokens
→ 40% lower API costs

All by delegating code search to a tiny agent.

Here's how 🧵

[Maxence Lasbordes @maxencelsb]

@maximelabonne Congrats on the release! 🫡

[Maxence Lasbordes @maxencelsb]

@MiaAI_lab Thanks for sharing our work!! Hope you find it useful 🙂

[Maxence Lasbordes @maxencelsb]

@CavaillesAdrien Thanks Adrien 😁

[Maxence Lasbordes @maxencelsb]

🚀 Introducing ColGrep-Agent-2B!

An open 2B model, now integrated into NextPlaid via ColGrep, that runs locally to make coding agents more efficient.

With Claude Code:

→ 34% fewer API tokens
→ 40% lower API costs

All by delegating code search to a tiny agent.

Here's how 🧵

[Maxence Lasbordes @maxencelsb]

@staghado Thanks Said !!🫡

[Maxence Lasbordes @maxencelsb]

@paulomouraj @Aarush1003 @raphaelsrty @AmelieTabatta Thanks bro🫶 u next

[Amélie Chatelain @AmelieTabatta]

Should you waste tokens having your coding agent use grep, or hand the search to a tiny local model?

We release ColGrep-Agent-2B! A code-search agent that runs locally, searches with ColGrep, reads files, & returns locations + code to your main agent
-> 34% fewer API tokens

[Raphaël Sourty @raphaelsrty]

Introducing colgrep-agent-2B ☺️

ColGREP is a multi-vector search tool built for coding agents. It’s a hybrid grep that combines grep features with multi-vector retrieval. Runs 100% locally

Open-sourcing a 2B-parameter ColGREP expert model to serve as a model-in-the-middle 🧵

[Maxence Lasbordes @maxencelsb]

Huge thanks to my co-authors @raphaelsrty, @Aarush1003, and @AmelieTabatta for their incredible work! 🚀

🤗 Model:
https://t.co/IZ77bFn0AX
📝 Blog post:
https://t.co/GXIivJ8jFF
💻 GitHub:
https://t.co/y8gkO6yLpa
📄 Paper:
https://t.co/GDSadlM6yp

[Maxence Lasbordes @maxencelsb]

📄 In parallel, we also released a research paper!

It explores how small, specialized agents can leverage semantic search for efficient, multilingual code localization.

Check out the paper for more details! ↓

https://t.co/GDSadlM6yp

[LightOn @LightOnIO]

50 million downloads on @huggingface!

LightOn SOTA late-interaction and dense retrievers, OCR models, and LLMs are validated by the community and tested every day in production.

🧪 LightOn is now one of the most active labs in the world in retrieval, pushing the Pareto frontier of AI, always open source.

🙌 Huge kudos to @iacopo_poli, @AmelieTabatta, @antoine_chaffin, @raphaelsrty, @staghado, @CavaillesAdrien, @baptaubertin, Maxence Lasbordes, @paulomouraj and the entire team for the work!

🔥 As proud as LightOn is of this milestone, the model is only one building block. Orchestration is what makes AI systems work.

Now it’s your turn to test them in production: https://t.co/RNJQKEHzQ2

[Maxence Lasbordes @maxencelsb]

@staghado Congrats on the release it's crazy 🫡

[LightOn @LightOnIO]

World-leading document recognition. Beyond text extraction.

Introducing LightOnOCR-3, our new family of state-of-the-art AI models for document intelligence.
Building on LightOnOCR-2, it recognizes text and handwriting, describes images, extracts data from charts and preserves document structure, all in a single processing step.

🏆 Leading benchmark results : ahead of Chandra-OCR-2, Mistral OCR 4.1 and dots.mocr on OlmOCR-Bench, and first among open-weight models on ParseBench.

📊 More information from every document : turn text, tables, images and charts into content your business applications can use.

⚡Compact and efficient: 0.8B and 4B versions, with document processing up to twice as fast as LightOnOCR-2.

🔓Apache 2.0 license: use, adapt and deploy the models on your own infrastructure.

From handwritten administrative files to financial reports and technical documents, make more of your information searchable and usable.

👉 Explore the models and benchmark results: https://t.co/xXJD1Eo9XA

👉🏻Explore the model page on our Website : https://t.co/y5ZWMpMOL9

#LightOn #DocumentIntelligence #OCR