Skip to content

OwOpeepeepoopoo

ttrl-qwen3.5-0.8b-math-l1

OwOpeepeepoopoo/ttrl-qwen3.5-0.8b-math-l1

ttrl-qwen3.5-0.8b-math-l1 is a text generation model from OwOpeepeepoopoo. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.

Reproduction of "TTRL: Test-Time Reinforcement Learning" (arXiv:2504.16084) on a fresh 2026 base model (Qwen/Qwen3.5-0.8B-Base), trained on MATH-L1 with NO ground-truth labels, on a single H100.

Downloads · 30 days

0

Access

Public

Updated Jun 23, 2026

Repo size

124 KB

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.png244 KB · 87%

At a glance

Task
Text Generation
License
apache-2.0
Access
Public
Created
Jun 23, 2026
Updated
Jun 23, 2026
SHA
22946b9d

Try a prompt

Base models

Task
Text Generation
License
apache-2.0
Languages
en
Created
Jun 23, 2026
Updated
Jun 23, 2026