---
base_model:
- Qwen/Qwen3-VL-8B-Instruct
license: cc-by-nc-4.0
pipeline_tag: video-text-to-text
library_name: transformers
tags:
- video-understanding
- drama
- reasoning
- reinforcement-learning
---

# SAGA_Qwen3-8B

SAGA-finetuned **Qwen3-VL-8B** model for short-drama video understanding, trained on the [M-Drama](https://huggingface.co/datasets/yixin1121/M-Drama) dataset (SFT + RL).

This model is introduced in [Beyond Sparse Rewards: A New Benchmark and Structure-Aware Graph Alignment for Micro-Drama Understanding](https://huggingface.co/papers/2609.07107).  
Code: [github.com/qyx1121/MDrama_SAGA](https://github.com/qyx1121/MDrama_SAGA)

## Usage

```python
from transformers import AutoProcessor, AutoModelForImageTextToText
import torch

model = AutoModelForImageTextToText.from_pretrained(
    "yixin1121/SAGA_Qwen3-8B", torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained("yixin1121/SAGA_Qwen3-8B")
```

## Training

- **Base model:** Qwen3-VL-8B-Instruct
- **Training data:** [M-Drama](https://huggingface.co/datasets/yixin1121/M-Drama) — 32,361 QA annotations over 8,102 short-drama video clips
- **Pipeline:** SFT followed by RL (DAPO-style, with graph-structure and semantic rewards)

## License

CC BY-NC 4.0. This model is intended for research purposes only.