|
--- |
|
{} |
|
--- |
|
[](https://github.com/bfshi/scaling_on_scales) |
|
|
|
# When Do We Not Need Larger Vision Models? |
|
|
|
## Model |
|
|
|
This is a LLaVA-v1.5-13b model trained with [S<sup>2</sup>-Wrapper](https://github.com/bfshi/scaling_on_scales), a simple approach to enable any vision model to perceive high-resolution images. We use image resolutions of up to 1008x1008 for this model. |
|
|
|
## Training |
|
|
|
The training pipeline and dataset completely follow [LLaVA-v1.5](https://github.com/haotian-liu/LLaVA/tree/main). We use LoRA to fine-tune the model. |
|
|
|
## Benchmarking |
|
|
|
| Version | Size | Schedule | Checkpoint | VQAv2 | VizWiz | TextVQA | MMMU-val | MathVista | MM-Bench | SEED | MM-Vet | |
|
|----------|----------|-----------|-----------|---|---|---|---|---|---|---|---| |
|
| LLaVA-1.5 | 13B | full_ft-1e | [liuhaotian/llava-v1.5-13b](https://huggingface.co/liuhaotian/llava-v1.5-13b) | 80.0 | 53.6 | 61.3 | 36.4 | 27.6 | 67.7 | 68.2 | 36.1 | |
|
| LLaVA-1.5 | 13B | lora-1e | [liuhaotian/llava-v1.5-13b-lora](https://huggingface.co/liuhaotian/llava-v1.5-13b-lora) | 80.0 | 58.9 | 60.2 | - | - | 68.5 | - | 38.3 | |
|
| LLaVA-1.5-S2 | 13B | lora-1e | this model | **80.9** | 56.0 | **63.1** | **37.4** | **27.8** | 67.9 | **68.9** | 36.4 | |
|
## License |
|
Llama 2 is licensed under the LLAMA 2 Community License, |
|
Copyright (c) Meta Platforms, Inc. All Rights Reserved. |
|
|
