| | --- |
| | license: apache-2.0 |
| | datasets: |
| | - lmms-lab/LLaVA-Video-178K |
| | language: |
| | - en |
| | base_model: |
| | - Qwen/Qwen2-VL-7B |
| | tags: |
| | - qwen2_vl |
| | - multimodal |
| | - conversational |
| | --- |
| | |
| | # Model Card |
| |
|
| | This model is obtained by fine-tuning [Qwen2-VL-7B-Base](https://huggingface.co/Qwen/Qwen2-VL-7B) on [LLaVA-Video-178K](https://huggingface.co/datasets/lmms-lab/LLaVA-Video-178K). It is used as a comparison baseline in [LiveCC](https://showlab.github.io/livecc) project. |
| |
|
| | # Performance |
| |
|
| |
|
| |
|
| | # Acknowledgement |
| |
|
| | [Joya Chen](https://chenjoya.github.io/) built the training code, and Yiqi Lin trained the model. The QA evaluation is done by [Joya Chen](https://chenjoya.github.io/), and CC evaluation is done by Ziyun Zeng. Infra is supported by the company. |
