Maxime Labonne's picture

Maxime Labonne PRO

mlabonne

·

https://mlabonne.github.io/blog

AI & ML interests

Post-training, model editing, quantization

Organizations

upvoted a paper 4 days ago

LFM2 Technical Report

Paper • 2511.23404 • Published 8 days ago • 34

upvoted a collection 8 days ago

Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability

A compilation of sparse auto-encoders trained on large language models. • 34 items • Updated Oct 10 • 4

upvoted an article 10 days ago

Article

Continuous batching from first principles

+1

12 days ago

•

240

upvoted 2 collections about 1 month ago

LFM2

15 items • Updated Jul 12 • 3

🔈 LFM2-Audio

End-to-end audio foundation model, designed for low latency and real-time conversations • 3 items • Updated 4 days ago • 8

upvoted 2 articles about 1 month ago

Article

Projected Abliteration

Oct 25

•

30

Article

Building the Open Agent Ecosystem Together: Introducing OpenEnv

+8

Oct 23

•

134

upvoted a collection about 2 months ago

💧 LFM2

Models made at Liquid AI • 8 items • Updated Oct 8 • 2

upvoted an article 2 months ago

Article

Introducing RTEB: A New Standard for Retrieval Evaluation

+4

Oct 1

•

128

upvoted a collection 2 months ago

⚛️ Liquid Nanos

Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices • 22 items • Updated 4 days ago • 97

upvoted an article 3 months ago

Article

SmolLM3: smol, multilingual, long-context reasoner

+21

Jul 8

•

734

upvoted a collection 3 months ago

Luth x LFM2

6 items • Updated Sep 24 • 14

upvoted an article 4 months ago

Article

Luth: Efficient French Specialization for Small Language Models

Aug 11

•

18

upvoted 2 collections 4 months ago

LFM2-VL

10 items • Updated Aug 16 • 1

VYVO-LFM2-TTS

13 items • Updated Aug 21 • 4

upvoted an article 4 months ago

Article

The Hallucinations Leaderboard, an Open Effort to Measure Hallucinations in Large Language Models

+4

Jan 29, 2024

•

33

upvoted a collection 4 months ago

👁️ LFM2-VL

LFM2-VL is our first series of vision-language models, designed for on-device deployment. • 10 items • Updated 4 days ago • 58

upvoted 2 articles 5 months ago

Article

Unlocking Healthcare AI: I'm Releasing State-of-the-Art Medical Models for Free. Forever.

Jul 16

•

144

Article

Building the Hugging Face MCP Server

+2

Jul 10

•

66

upvoted a collection 5 months ago

Releases July 11

20 items • Updated Jul 14 • 2