|
---
|
|
license: apache-2.0
|
|
inference: false
|
|
datasets:
|
|
- Lin-Chen/ShareGPT4V
|
|
pipeline_tag: image-text-to-text
|
|
---
|
|
<br>
|
|
<br>
|
|
|
|
# open-llava-next-llama3-8b Model Card
|
|
|
|
## Model details
|
|
|
|
**Model type:**
|
|
open-llava-next-llama3-8b is an open-source implementation chatbot trained by fine-tuning the entire model on open-source [Open-LLaVA-Next-mix1M](https://huggingface.co/datasets/Lin-Chen/Open-LLaVA-NeXT-mix1M) data.
|
|
|
|
**Model date:**
|
|
open-llava-next-llama3-8b was trained in May 2024.
|
|
|
|
**Paper or resources for more information:**
|
|
[[Code](https://github.com/xiaoachen98/Open-LLaVA-NeXT)]
|
|
|
|
| Name | ViT | LLM | Weights | MME | SEED | SQA | MMB | MMB-CN | TextVQA | GQA |
|
|
|---|---|---|---|---|---|---|---|---|---|---|
|
|
| llava-next-vicuna-7b | CLIP-L-336 | Vicuna-7B | [HF](https://huggingface.co/liuhaotian/llava-v1.6-vicuna-7b) | 1519 | 70.2 | 70.1 | 67.4 | 60.6 | 64.9 | 64.2 |
|
|
| open-llava-next-vicuna-7b| CLIP-L-336 | Vicuna-7B | [HF](https://huggingface.co/Lin-Chen/open-llava-next-vicuna-7b) | 1540 | 71.1 | 70.7 | 68.5 | 60.7 | 67.2 | 64.3 |
|
|
| open-llava-next-llama3-8b| CLIP-L-336 | LLaMA3-8B | [HF](https://huggingface.co/Lin-Chen/open-llava-next-llama3-8b) | 1552 | 74.4 | 77.3 | 74.4 | 70.4 | 69.8 | 65.9 |
|
|
|
|
## Usage
|
|
|
|
You can utilize this model as we provide in our [[repository](https://github.com/xiaoachen98/Open-LLaVA-NeXT)]. Moreover, you can direct load this model and use it in the [[LLaVA repository](https://github.com/haotian-liu/LLaVA)].
|
|
|
|
## Training dataset
|
|
|
|
All training data are open-sourced in our [repository](https://github.com/xiaoachen98/Open-LLaVA-NeXT).
|
|
|
|
- [ShareGPT4V Mix665K](https://huggingface.co/datasets/Lin-Chen/ShareGPT4V)
|
|
- 200K GPT4V-generated instruction data (ALLaVA)
|
|
- 200K various VQA data
|
|
|
|
## Intended use
|
|
|
|
**Primary intended uses:**
|
|
The primary use of open-llava-next-llama3-8b is research on large multimodal models and chatbots.
|
|
|
|
**Primary intended users:**
|
|
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
|
|
|
