---
library_name: transformers
license: apache-2.0
datasets:
- liuhaotian/LLaVA-Instruct-150K
- liuhaotian/LLaVA-Pretrain
language:
- en
---

# Model Card for OpenHermes-7B-llava-instruct

<!-- Provide a quick summary of what the model is/does. -->



## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->


- **Developed by:** [LAION](https://laion.ai/), [SkunkworksAI](https://huggingface.co/SkunkworksAI)
- **Model type:** LLaVA is an open-source chatbot trained by fine-tuning OpenHermes on GPT-generated multimodal instruction-following data.
It is an auto-regressive language model, based on the transformer architecture
- **Finetuned from model:** [OpenHermes-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
- **Finetuned from model:** Apache-2.0

### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** [BakLLaVa](https://github.com/SkunkworksAI/BakLLaVA)

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->
| model |	SQA |	POPE |	GQA |
| --- | --- | --- | --- |
| llava-1.5-7b |	67.97%	| 85.30% |	61.96% |
| openhermes-7b-llava-instruct-665k |	59.64% |	84.60% |	42.39% |