Lewis Tunstall's picture

Lewis Tunstall PRO

lewtun

·

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

AI & ML interests

LLMs, LLMs, LLMs

Recent Activity

liked a model 2 days ago

kernels-community/vllm-flash-attn3

liked a model 2 days ago

moonshotai/Kimi-K2-Thinking

upvoted an article 4 days ago

Ultra-Long Sequence Parallelism: Ulysses + Ring-Attention Technical Principles and Implementation

View all activity

Organizations

lewtun 's models 288

lewtun/Qwen3-32B-SFT-20250908120312

lewtun/Qwen3-0.6B-SFT-20250908114642

Text Generation • 0.6B • Updated Sep 8 • 12

lewtun/Qwen3-32B-SFT-20250908115917

lewtun/SmolLM2-135M-Instruct-SFT-Trackio-Test

Text Generation • 0.1B • Updated Aug 7 • 7

lewtun/Qwen3-0.6B-SFT-Trackio-Test

Text Generation • 0.6B • Updated Aug 7 • 19

lewtun/Qwen3-0.6B-SFT-Demo

Text Generation • 0.6B • Updated Aug 7 • 19

lewtun/zephyr-7b-gemma-dpo

lewtun/zephyr-7b-gemma-sft

lewtun/smollm2-360M-sft

lewtun/smollm2-1.7B-sft

lewtun/smollm-360M-instruct-new

lewtun/mistral-7b-sft-constitutional-ai

lewtun/mistral-7b-dpo-constitutional-ai

lewtun/zephyr-7b-sft-full

Text Generation • 266k • Updated Jul 24 • 1

lewtun/Qwen2.5-1.5B-Open-R1-Distill

Text Generation • 2B • Updated Apr 16

lewtun/does-deepspeed-still-work-sft

Text Generation • 2B • Updated Apr 16 • 1

lewtun/Llama-3.2-1B-SFT-Capybara-No-Packing-Llama

Text Generation • 1B • Updated Apr 16 • 2

lewtun/Qwen2.5-1.5B-SFT-Capybara-No-Packing

Text Generation • 2B • Updated Apr 15 • 3

lewtun/Llama-3.2-1B-SFT-Capybara-No-Packing-ChatML

Text Generation • 1B • Updated Apr 15 • 2

lewtun/Qwen2.5-7B-Instruct-GRPO

lewtun/Qwen2.5-Math-1.5B-Instruct-GRPO

lewtun/dummy-config-test

Text Generation • Updated Feb 20

lewtun/Qwen2.5-1.5B-Open-R1-Code-GRPO

lewtun/smollm2-distill-default-chat-template

Text Generation • 2B • Updated Feb 17

lewtun/qwen2.5-1.5b-distill-default-chat-template

2B • Updated Feb 17 • 1

lewtun/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

2B • Updated Feb 7

lewtun/Qwen-2.5-7B-Simple-RL

lewtun/DeepSeek-R1-Distill-Qwen-7B-GRPO

lewtun/Qwen2.5-1.5B-Open-R1-GRPO

lewtun/Qwen2-0.5B-SFT

Updated Oct 17, 2024