Hugging Face's logo

DarthZhu
/
VideoRLVR-Wan2.2-Base

Image-to-Video
Diffusers
Safetensors
ti2v
Model card Files
xet
 Community
1
DarthZhu commited on
Commit
540da95
·
verified ·
1 Parent(s): 705ce8d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -12,7 +12,7 @@ datasets:
12
 
13
  VideoRLVR is a reinforcement learning (RL) recipe for training video reasoning models with verifiable rewards, introduced in the paper [Video Models Can Reason with Verifiable Rewards](https://huggingface.co/papers/2605.15458).
14
 
15
- This checkpoint is an RL-optimized version of [Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B) trained on procedurally generated reasoning tasks including Maze, FlowFree, and Sokoban.
16
 
17
  - **Paper:** [Video Models Can Reason with Verifiable Rewards](https://huggingface.co/papers/2605.15458)
18
  - **Project Page:** [https://darthzhu.github.io/VideoRLVR-page/](https://darthzhu.github.io/VideoRLVR-page/)
 
12
 
13
  VideoRLVR is a reinforcement learning (RL) recipe for training video reasoning models with verifiable rewards, introduced in the paper [Video Models Can Reason with Verifiable Rewards](https://huggingface.co/papers/2605.15458).
14
 
15
+ This checkpoint is an SFT version of [Wan2.2-TI2V-5B](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B) trained on procedurally generated reasoning tasks including Maze, FlowFree, and Sokoban.
16
 
17
  - **Paper:** [Video Models Can Reason with Verifiable Rewards](https://huggingface.co/papers/2605.15458)
18
  - **Project Page:** [https://darthzhu.github.io/VideoRLVR-page/](https://darthzhu.github.io/VideoRLVR-page/)