PRIMO-R1-7B

LeonOverload/PRIMO-R1-7B

Video Text To Text8.3B parametersLicense: apache-2.0
Tracked by OpenModelStats since September 3, 2026View on Hugging Face ↗
Downloads 30D
185
Total downloads
229
Gained 7D
0
Gained 30D
—
Likes
1
+0 in 7D
Rank · tracked models
—
–this week
Parameters
8.3B
Last source update
Sep 4, 2026

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-03. Charts appear as daily observations accumulate.

Overview

PRIMO-R1-7B is a video text to text model published by LeonOverload. OpenModelStats has tracked the model since Sep 3, 2026, most recently observing it Sep 4, 2026.

Published
Mar 16, 2026
Last updated
Sep 4, 2026
Library
—
License
apache-2.0
Task
Video Text To Text
Parameters
8,292,166,656
Spaces
—
Derivative models
—
Velocity 7D/day
0
safetensorsqwen2_5_vlrobotic-manipulationreinforcement-learningchain-of-thoughtvideo-text-to-textdataset:LeonOverload/primo-bench-jsondataset:LeonOverload/primo-sft-jsondataset:LeonOverload/primo-video-mediaarxiv:2603.15600base_model:Qwen/Qwen2.5-VL-7B-Instructbase_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct

Publisher

LeonOverloadView publisher statistics →

Derived from Qwen/Qwen2.5-VL-7B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to PRIMO-R1-7B
ModelDL 30D
TimeLens-7BTencentARC924
SkyCaptioner-V1Skywork360
VideoChat-R1_5-7BOpenGVLab258
qwen2.5-vl-7b-cam-motionchancharikm235
VideoChat-R1_7B_captionOpenGVLab44
VideoScore-v1.1TIGER-Lab992