README.md

metadata

title: TwIL-LM3
emoji: 🧠
colorFrom: indigo
colorTo: blue
sdk: gradio
sdk_version: 6.22.0
app_file: app.py
pinned: true
license: other
short_description: Official demo of TwIL-LM3, a 3B formal-logic reasoner
python_version: '3.12'
startup_duration_timeout: 30m

TwIL-LM3 — Official Demo

Official Hugging Face Space for webAI-Official/TwIL-LM3, webAI's 3B reasoning model for formal logic.

TwIL-LM3 is built from HuggingFaceTB/SmolLM3-3B through LoRA SFT, checkpoint fusion, WiSE-FT interpolation, and entropy-weighted GRPO. It emits a collapsible <think>…</think> trace before the answer.

Temperature = 0 (greedy) matches the published evaluation protocol. Keep max new tokens at 2048 or higher so the reasoning block is not truncated.

This Space runs on ZeroGPU and streams tokens as they are generated.

License: the model is released under the webAI Non-Commercial License ver. 1.0 — see the model repository for full terms.