---
license: mit
datasets:
- liuhaotian/LLaVA-Instruct-150K
- LanguageBind/Video-LLaVA
language:
- en
metrics:
- accuracy
pipeline_tag: image-text-to-text
library_name: transformers
---
# LSTP-Chat: Language-guided Spatial-Temporal Prompt Learning for Video Chat

Available Models:

- LSTP-FlanT5xl
- LSTP-Chat-7B (Vicuna-7b)

For more details, please refer to our [official repository](https://github.com/bigai-nlco/LSTP-Chat)