384 143 945

Maxime Labonne PRO

mlabonne

https://mlabonne.github.io/blog

AI & ML interests

Post-training, model editing, quantization

Recent Activity

upvoted an article 11 minutes ago

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

liked a Space 1 day ago

prithivMLmods/LFM2-VL-Demo

posted an update 1 day ago

Liquid just released two 450M and 1.6B param VLMs! They're super fast and leverage SigLIP2 NaFlex encoders to handle native resolutions without distortion. It's ideal for on-device deployment in constrained environments like phones. It's available today on Hugging Face, with an inference and a fine-tuning Colab notebooks. https://huggingface.co/LiquidAI/LFM2-VL-450M https://huggingface.co/LiquidAI/LFM2-VL-1.6B

View all activity

Organizations

upvoted an article 11 minutes ago

Article

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

and 5 others •

Jan 29, 2024

• 31

upvoted a collection 2 days ago

👁️ LFM2-VL

Collection

LFM2-VL is our first series of vision-language models, designed for on-device deployment. • 2 items • Updated 2 days ago • 18

upvoted 2 articles 29 days ago

Article

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

•

29 days ago

• 133

Article

Building the Hugging Face MCP Server

and 3 others •

Jul 10

• 59

upvoted 3 collections about 1 month ago

upvoted a collection 5 months ago

🧠 Reasoning datasets

Collection

Datasets with reasoning traces for math and code released by the community • 24 items • Updated May 19 • 162

upvoted an article 5 months ago

Article

Open R1: Update #3

and 9 others •

Mar 11

• 295

upvoted a paper 5 months ago

Atom of Thoughts for Markov LLM Test-Time Scaling

Paper • 2502.12018 • Published Feb 17 • 17

upvoted an article 6 months ago

Article

Open-source DeepResearch – Freeing our search agents

and 4 others •

Feb 4

• 1.28k

upvoted a paper 6 months ago

WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training

Paper • 2501.18511 • Published Jan 30 • 20

upvoted 4 articles 7 months ago

Article

Reverse-engineering Custom-GPT prompts

•

Jan 27

• 9

Article

SmolVLM Grows Smaller – Introducing the 250M & 500M Models!

and 2 others •

Jan 23

• 182

Article

Making ML-powered web games with Transformers.js

•

Jul 5, 2023

• 13

Article

The Large Language Model Course

•

Jan 16

• 199

upvoted a paper 7 months ago

Enhancing Human-Like Responses in Large Language Models

Paper • 2501.05032 • Published Jan 9 • 57

upvoted 2 articles 9 months ago

Article

The Beginners Guide to Cleaning a Dataset

•

Nov 18, 2024

• 24

Article

Releasing the largest multilingual open pretraining dataset

and 2 others •

Nov 13, 2024

• 102

upvoted an article 10 months ago

Article

Decoding Strategies in Large Language Models

•

Oct 29, 2024

• 77

Maxime Labonne PRO

AI & ML interests

Recent Activity

Organizations

mlabonne's activity

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

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

Building the Hugging Face MCP Server

Open R1: Update #3

Open-source DeepResearch – Freeing our search agents

Reverse-engineering Custom-GPT prompts

SmolVLM Grows Smaller – Introducing the 250M & 500M Models!

Making ML-powered web games with Transformers.js

The Large Language Model Course

The Beginners Guide to Cleaning a Dataset

Releasing the largest multilingual open pretraining dataset

Decoding Strategies in Large Language Models