Downloads · 30 days
15
11% of all-time downloads
VideoSSR
yhx12/VideoSSR
VideoSSR is a machine learning model from yhx12. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
VideoSSR-8B is a multimodal large language model (MLLM) fine-tuned from Qwen-VL-8B-Instruct for enhanced video understanding. It is trained using a novel Video Self-Supervised Reinforcement Learning (VideoSSR) framewo…
All-time downloads
135
Public
Parameters
8.8B
17.5 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors17.5 GB · 100%
At a glance
- Model type
- qwen3_vl
- Access
- Public
- Created
- Nov 9, 2025
- Updated
- Nov 11, 2025
- SHA
- f3257c9f
Model card
From the Hugging Face model README
VideoSSR-8B is a multimodal large language model (MLLM) fine-tuned from Qwen-VL-8B-Instruct for enhanced video understanding. It is trained using a novel Video Self-Supervised Reinforcement Learning (VideoSSR) framework, which generates its own high-quality training data directly from videos, eliminating the need for manual annotation.
- Base Model:
Qwen-VL-8B-Instruct - Paper: VideoSSR: Video Self-Supervised Reinforcement Learning
- Code: https://github.com/lcqysl/VideoSSR
- Type
- qwen3_vl
- Created
- Nov 9, 2025
- Updated
- Nov 11, 2025