Skip to content

logan7000

mllm-mmr1-ttrl-qwen25vl-3b-full-best-s100

logan7000/mllm-mmr1-ttrl-qwen25vl-3b-full-best-s100

mllm-mmr1-ttrl-qwen25vl-3b-full-best-s100 is a reinforcement learning model from logan7000. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

Fine-tuned from Qwen/Qwen2.5-VL-3B-Instruct with TTRL / un-GRPO-maj: no labels, trained against the model's own self-consistency majority over its rollouts.

Downloads · 30 days

13

27% of all-time downloads

All-time downloads

48

Public

Parameters

756K

7.5 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors7.5 GB · 100%

At a glance

Task
Reinforcement Learning
License
apache-2.0
Model type
qwen2_5_vl
Access
Public
Created
Aug 9, 2026
Updated
Aug 9, 2026
SHA
c95d7901

Base models

Task
Reinforcement Learning
Type
qwen2_5_vl
License
apache-2.0
Created
Aug 9, 2026
Updated
Aug 9, 2026