Skip to content

logan7000

mllm-mmr1-ttrl-qwen25vl7b

logan7000/mllm-mmr1-ttrl-qwen25vl7b

mllm-mmr1-ttrl-qwen25vl7b is a image-text-to-text model from logan7000. Use it for the image-text-to-text 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.

- Base: Qwen/Qwen2.5-VL-7B-Instruct - Method: TTRL (label-free GRPO with self-consistency majority-vote pseudo-labels) - Dataset: mmr1 (~8k), 1 epoch - Checkpoint: best (bestmodel) - 4-bench avg: 48.24 - best repo: q1…

Downloads · 30 days

7

12% of all-time downloads

All-time downloads

58

Public

Parameters

849K

16.6 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors16.6 GB · 100%

At a glance

Task
Image-Text-to-Text
License
apache-2.0
Model type
qwen2_5_vl
Access
Public
Created
Jul 22, 2026
Updated
Aug 9, 2026
SHA
6b9cd4ed

Try a prompt

Base models

Task
Image-Text-to-Text
Type
qwen2_5_vl
License
apache-2.0
Created
Jul 22, 2026
Updated
Aug 9, 2026