🔄 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

lewtun 's models 330

lewtun/tailsft-repro-olmo2-1b-tail70

Text Generation • 1B • Updated Sep 15 • 13

lewtun/tailsft-repro-olmo2-1b-tail50

Text Generation • 1B • Updated Sep 15 • 35

lewtun/tailsft-repro-olmo2-1b-std

Text Generation • 1B • Updated Sep 15 • 9

lewtun/tailsft-repro-smoke-tail50

Text Generation • 1B • Updated Sep 15 • 16

lewtun/tailsft-repro-smoke-std

Text Generation • 1B • Updated Sep 15 • 10

lewtun/carbon-14b-sft-smoke-20260805-124457

Text Generation • 15B • Updated Aug 5 • 8

lewtun/qwen3-0.6b-wordle-grpo

Text Generation • 0.6B • Updated Jun 18 • 25

lewtun/Qwen3-4B-Capybara-SFT

Text Generation • 4B • Updated Jun 18 • 39 • 1

lewtun/qwen3-4b-capybara

Text Generation • 4B • Updated Jun 18 • 36 • 1

lewtun/qwen3-0.6b-capybara-smoke

Text Generation • 0.6B • Updated Jun 8 • 27

lewtun/qwen3-0.6b-capybara

Text Generation • 0.6B • Updated Jun 7 • 15

lewtun/qwen3-0.6b-capybara-1step

Text Generation • 0.6B • Updated Jun 7 • 36

lewtun/qwen3-0.6b-angrygiraffe-sft

Text Generation • 0.6B • Updated Jun 3 • 36

lewtun/qwen3-4b-hermes-tooluse

Text Generation • 4B • Updated Jun 3 • 17

lewtun/qwen3-0.6b-sft-capybara

Text Generation • 0.6B • Updated May 12 • 24

lewtun/smollm2-1.7b-capybara-sft

lewtun/qwen3-0.6b-openthoughts3-sft

lewtun/smollm2-135m-capybara-csv

Text Generation • 0.1B • Updated May 11 • 16 • 1

lewtun/smollm2-135m-capybara-jsonl

Text Generation • 0.1B • Updated May 11 • 35

lewtun/SmolLM2-360M-Instruct-capybara-sft

lewtun/SmolLM2-360M-OpenMathReasoning

Text Generation • 0.4B • Updated May 11 • 33

lewtun/qwen3-0.6b-capybara-sft

Text Generation • 0.6B • Updated May 8 • 47

lewtun/qwen3-06b-ultrachat-sft

Text Generation • 0.6B • Updated May 8 • 10

lewtun/SmolLM2-135M-smoltalk-sft

lewtun/SmolLM2-1.7B-Snappy-Lyte

lewtun/SmolLM2-135M-SFT-Capybara-LoRA

lewtun/SmolLM2-1.7B-SmolTalk-SFT-LoRA

lewtun/SmolLM2-135M-OpenThoughts-SFT

lewtun/SmolLM2-135M-Capybara-SFT

Text Generation • 0.1B • Updated May 7 • 58

lewtun/SmolLM2-135M-no-robots