🔄 In a Training Loop

Lewis Tunstall PRO

lewtun

huggingface

·

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

AI & ML interests

LLMs, LLMs, LLMs

Recent Activity

liked a Space 19 minutes ago

FineEnvs/MiMo-RL-Envs-Explorer

updated a Space about 19 hours ago

lewtun/trl-active-groups

published a Space about 19 hours ago

lewtun/trl-active-groups

View all activity

Organizations

liked a Space 19 minutes ago

MiMo RL Environment Explorer

Explore the MiMo-V2.6 RL environments and run rollouts

liked a dataset 1 day ago

XiaomiMiMo/MiMo-V2.6-RL-oss

Viewer • Updated 3 days ago • 7.78k • 22.6k • 520

liked a dataset 3 days ago

FineEnvs/SmolDataEnvs

RL Environment • Updated 2 days ago • 5.39k • 2.46k • 55

liked a model about 1 month ago

zai-org/GLM-5.3-Flash

Image-Text-to-Text • 321B • Updated 22 days ago • 4.52M • • 2.59k

liked 2 models about 2 months ago

Qwen/Qwen3.8-2.4T-A95B

Text Generation • 2.4T • Updated Aug 12 • 43.6k • • 1.27k

meta-models/Muse-Glimmer-30B

Image-Text-to-Text • 30B • Updated Aug 11 • 277k • • 1.96k

liked a Space about 2 months ago

SAIR Stage 2 Agent Collab

Making Open-Weight LLMs better at Formal Math

liked a Space 2 months ago

Anatomy Of Frontier Lab Model Intrusion

Replay a detailed security incident timeline

liked a model 2 months ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 27 days ago • 1.51M • • 11.5k

liked a dataset 2 months ago

HuggingFaceCode/stack-v3-train

Viewer • Updated 4 days ago • 173M • 179k • 383

liked a Space 2 months ago

cowrite

Collaborate on docs with AI suggestions and comments

liked a dataset 2 months ago

huggingface/forensic-refusal

Traces • Updated Jul 20 • 2 • 248 • 14

liked a Space 2 months ago

Reproducing ICML 2026

Reproduce every ICML 2026 paper with your agent

liked a Space 3 months ago

Don't Train the Model, Evolve the Harness

Evolving an agent's harness, not its model, on Harvey's LAB

liked a model 3 months ago

thinkingmachines/Inkling

Image-Text-to-Text • 952B • Updated Jul 23 • 619k • • 1.79k

liked 5 Spaces 3 months ago

An Open Realtime Voice You Can Actually Run Yourself

Generate real‑time spoken AI conversations

RL-for-LLMs Wiki

A beautiful reader for the RL-for-LLMs knowledge base

RL-for-LLMs Wiki

Agents collaboratively build an expert-level, citation-backe

The Gemma Challenge and the Case for Agent Collabs

Running an open agent collaboration to speed up Gemma 4

Encoder-Free VLM

Train Your Own Encoder-Free VLM in $100