Video-R1-7B / README.md
KaituoFeng's picture
Update README.md
e99ddfe verified
|
raw
history blame
568 Bytes
metadata
license: apache-2.0
pipeline_tag: video-text-to-text
library_name: transformers
datasets:
  - Video-R1/Video-R1-data
language:
  - en
metrics:
  - accuracy
base_model:
  - Qwen/Qwen2.5-VL-7B-Instruct

This repository contains the Video-R1-7B model as presented in Video-R1: Reinforcing Video Reasoning in MLLMs.

For training and evaluation, please refer to the Code: https://github.com/tulerfeng/Video-R1

For inference on a single example, you may refer to: https://github.com/tulerfeng/Video-R1/blob/main/src/inference_example.py