🔄 In a Training Loop

Lewis Tunstall PRO

lewtun

huggingface

·

https://lewtun.github.io/blog/

AI & ML interests

LLMs, LLMs, LLMs

Recent Activity

updated a bucket 2 days ago

lewtun/trl-pr-7901-bucket

liked a Space 2 days ago

trl-lib/async-grpo-stable

upvoted an article 2 days ago

Yang-Mills, OpenAI proof, and the mass gap problem

View all activity

Organizations

upvoted an article 2 days ago

Article

Yang-Mills, OpenAI proof, and the mass gap problem

dlouapre

•

2 days ago

• 15

upvoted a paper 4 days ago

s^3: Simple Scaling of Swarms via Cooperative Multi-agent RL

Paper • 2611.08615 • Published 11 days ago • 1

upvoted an article 7 days ago

Article

Harness adapters: Safe RL for efficient agentic development

harness-hub

•

9 days ago

• 54

upvoted an article 12 days ago

Article

Announcing Project ProtoStar: Making Publicly Funded Science AI-Ready

+5

evijit, sayeedmd, gtananbaum, EmmaScharfmann, cgeorgiaw, EuniceML, irenesolaiman

•

18 days ago

• 42

upvoted a paper 13 days ago

Scaling Discovery through Test-Time Communication

Paper • 2609.21032 • Published Sep 17 • 1

upvoted a collection 16 days ago

🧬 FineDNA

The mid-training, SFT and RL data of Carbon-X, with the trained on it. Recipe: https://github.com/huggingface/carbon/tree/main/carbon-x • 4 items • Updated 14 days ago • 5

upvoted a paper 20 days ago

Score Centering Stabilizes Off-policy Reinforcement Learning

Paper • 2609.20807 • Published Sep 17 • 10

upvoted a collection 24 days ago

🧬 Carbon-X

Release artifacts for Carbon-X, the best open model for DNA understanding and generation • 7 items • Updated 17 days ago • 16

upvoted a paper 27 days ago

GitSwarm: Decentralized Compounding Inference

Paper • 2610.04862 • Published Oct 4 • 2

upvoted 2 articles about 1 month ago

Article

Carbon-A: Finding genes in known and unknown genomes

HuggingFaceBio

•

Oct 8

• 30

Article

Welcome RL Environments to the hub

+6

burtenshaw, AdithyaSK, sergiopaniego, xeophon, ryanmarten, merve, lhoestq, julien-c

•

Sep 28

• 46

upvoted an article about 2 months ago

Article

tokenizers v1: encode, decode and scaling, measured

+2

ArthurZ, sbrandeis, mcpotato, lysandre

•

Sep 21

• 97

upvoted an article 2 months ago

Article

Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL

+2

aminediroHF, qgallouedec, kashif, sergiopaniego

•

Sep 10

• 54

upvoted a paper 2 months ago

AI Research Preference Models

Paper • 2608.13940 • Published Aug 25 • 10

upvoted an article 2 months ago

Article

Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI

nico-martin, Xenova

•

Sep 1

• 99

upvoted a paper 3 months ago

Training AI Scientists to Replicate Research

Paper • 2608.13331 • Published Aug 13 • 3

upvoted an article 3 months ago

Article

State of Open Models: Summer 2026 Observations

+1

AdinaY, multimodalart, irenesolaiman

•

Aug 14

• 230

upvoted a paper 3 months ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published Jul 8 • 143

upvoted a collection 3 months ago

Muse Glimmer

Muse Glimmer 30B: multimodal agentic model for local deployment. BF16 weights, GGUF k-quants, ExecuTorch builds, DFlash drafter. • 4 items • Updated Aug 10 • 130

upvoted a paper 3 months ago

Understanding Reasoning from Pretraining to Post-Training

Paper • 2607.16097 • Published Jul 17 • 28