---
base_model: Qwen/Qwen3-VL-4B-Instruct
license: apache-2.0
library_name: transformers
pipeline_tag: video-text-to-text
tags:
- camera-movement
- video-understanding
- qwen3-vl
- sft
- vggt-injection
---

# CamInject-4B

This repository contains the **CamInject-4B** model from the paper [Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation](https://huggingface.co/papers/2608.10932).

**Project page**: https://ddz16.github.io/cammotion.github.io  
**GitHub**: https://github.com/ddz16/CamDistill

Camera-movement VGGT-Direct 注入 SFT 微调模型，基于 `Qwen/Qwen3-VL-4B-Instruct`。

- Checkpoint: `checkpoint-1326`
- 训练框架: [ms-swift](https://github.com/modelscope/ms-swift)

## 使用

```python
from transformers import AutoModelForCausalLM, AutoProcessor
model = AutoModelForCausalLM.from_pretrained("ddz16/CamInject-4B", torch_dtype="bfloat16", device_map="auto")
processor = AutoProcessor.from_pretrained("ddz16/CamInject-4B")
```