---
language:
- en
datasets:
- liuhaotian/LLaVA-Instruct-150K
pipeline_tag: image-text-to-text
arxiv: 2304.08485
license: llama2
tags:
- vision
- image-text-to-text
---
# llava-hf/llava-1.5-7b-hf
* Model creator: [llava-hf](https://huggingface.co/llava-hf)
* Original model: [llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf)
## Differences
* Added missing chat template to tokenizer_config.json
## License
Refer to the license of the original model card.