552 1 year ago

s1 is a reasoning model finetuned from Qwen2.5-32B-Instruct on just 1,000 examples. It matches o1-preview & exhibits test-time scaling via budget forcing.

tools
ollama run milkey/Simplescaling-S1

Applications

Claude Code
Claude Code ollama launch claude --model milkey/Simplescaling-S1
Codex
Codex ollama launch codex --model milkey/Simplescaling-S1
OpenCode
OpenCode ollama launch opencode --model milkey/Simplescaling-S1
OpenClaw
OpenClaw ollama launch openclaw --model milkey/Simplescaling-S1

Models

View all →

Readme