|
--- |
|
datasets: |
|
- liuhaotian/LLaVA-Pretrain |
|
- liuhaotian/LLaVA-Instruct-150K |
|
pipeline_tag: image-text-to-text |
|
library_name: xtuner |
|
--- |
|
|
|
<div align="center"> |
|
<img src="https://github.com/InternLM/lmdeploy/assets/36994684/0cf8d00f-e86b-40ba-9b54-dc8f1bc6c8d8" width="600"/> |
|
|
|
|
|
[](https://github.com/InternLM/xtuner) |
|
|
|
|
|
</div> |
|
|
|
## Model |
|
|
|
llava-llama-3-8b-hf is a LLaVA model fine-tuned from [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) and [CLIP-ViT-Large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) with [LLaVA-Pretrain](https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain) and [LLaVA-Instruct](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K) by [XTuner](https://github.com/InternLM/xtuner). |
|
|
|
**Note: This model is in official LLaVA format.** |
|
|
|
Resources: |
|
|
|
- GitHub: [xtuner](https://github.com/InternLM/xtuner) |
|
- HuggingFace LLaVA format model: [xtuner/llava-llama-3-8b-transformers](https://huggingface.co/xtuner/llava-llama-3-8b-transformers) |
|
- XTuner LLaVA format model: [xtuner/llava-llama-3-8b](https://huggingface.co/xtuner/llava-llama-3-8b) |
|
|
|
|
|
## Details |
|
|
|
| Model | Visual Encoder | Projector | Resolution | Pretraining Strategy | Fine-tuning Strategy | Pretrain Dataset | Fine-tune Dataset | |
|
| :-------------------- | ------------------: | --------: | ---------: | ---------------------: | ------------------------: | ------------------------: | -----------------------: | |
|
| LLaVA-v1.5-7B | CLIP-L | MLP | 336 | Frozen LLM, Frozen ViT | Full LLM, Frozen ViT | LLaVA-PT (558K) | LLaVA-Mix (665K) | |
|
| LLaVA-Llama-3-8B | CLIP-L | MLP | 336 | Frozen LLM, Frozen ViT | Full LLM, LoRA ViT | LLaVA-PT (558K) | LLaVA-Mix (665K) | |
|
| LLaVA-Llama-3-8B-v1.1 | CLIP-L | MLP | 336 | Frozen LLM, Frozen ViT | Full LLM, LoRA ViT | ShareGPT4V-PT (1246K) | InternVL-SFT (1268K) | |
|
|
|
|
|
## Results |
|
|
|
<div align="center"> |
|
<img src="https://github.com/InternLM/xtuner/assets/36994684/a157638c-3500-44ed-bfab-d8d8249f91bb" alt="Image" width=500" /> |
|
</div> |
|
|
|
| Model | MMBench Test (EN) | MMBench Test (CN) | CCBench Dev | MMMU Val | SEED-IMG | AI2D Test | ScienceQA Test | HallusionBench aAcc | POPE | GQA | TextVQA | MME | MMStar | |
|
| :-------------------- | :---------------: | :---------------: | :---------: | :-------: | :------: | :-------: | :------------: | :-----------------: | :--: | :--: | :-----: | :------: | :----: | |
|
| LLaVA-v1.5-7B | 66.5 | 59.0 | 27.5 | 35.3 | 60.5 | 54.8 | 70.4 | 44.9 | 85.9 | 62.0 | 58.2 | 1511/348 | 30.3 | |
|
| LLaVA-Llama-3-8B | 68.9 | 61.6 | 30.4 | 36.8 | 69.8 | 60.9 | 73.3 | 47.3 | 87.2 | 63.5 | 58.0 | 1506/295 | 38.2 | |
|
| LLaVA-Llama-3-8B-v1.1 | 72.3 | 66.4 | 31.6 | 36.8 | 70.1 | 70.0 | 72.9 | 47.7 | 86.4 | 62.6 | 59.0 | 1469/349 | 45.1 | |
|
|
|
## QuickStart |
|
|
|
### Chat by lmdeploy |
|
|
|
1. Installation |
|
``` |
|
pip install 'lmdeploy>=0.4.0' |
|
pip install git+https://github.com/haotian-liu/LLaVA.git --no-deps |
|
``` |
|
|
|
2. Run |
|
|
|
```python |
|
from lmdeploy import pipeline, ChatTemplateConfig |
|
from lmdeploy.vl import load_image |
|
pipe = pipeline('xtuner/llava-llama-3-8b-hf', |
|
chat_template_config=ChatTemplateConfig(model_name='llama3')) |
|
|
|
image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg') |
|
response = pipe(('describe this image', image)) |
|
print(response) |
|
``` |
|
|
|
More details can be found on [inference](https://lmdeploy.readthedocs.io/en/latest/inference/vl_pipeline.html) and [serving](https://lmdeploy.readthedocs.io/en/latest/serving/api_server_vl.html) docs. |
|
|
|
|
|
### Chat by CLI |
|
|
|
See [here](https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-hf/discussions/1)! |
|
|
|
|
|
## Citation |
|
|
|
```bibtex |
|
@misc{2023xtuner, |
|
title={XTuner: A Toolkit for Efficiently Fine-tuning LLM}, |
|
author={XTuner Contributors}, |
|
howpublished = {\url{https://github.com/InternLM/xtuner}}, |
|
year={2023} |
|
} |
|
``` |
|
|
