Downloads · 30 days
8
2% of all-time downloads
llava-v1.5-13b-s2-lora
bfshi/llava-v1.5-13b-s2-lora
llava-v1.5-13b-s2-lora is a text generation model from bfshi. Use it when you need the model to write or continue text. It is set up for transformers.
[](https://github.com/bfshi/scalingonscales)
All-time downloads
356
Public
Repo size
1.1 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin1.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llava
- Access
- Public
- Created
- May 3, 2024
- Updated
- May 3, 2024
- SHA
- 14a87c33
Try a prompt
Model card
From the Hugging Face model README
When Do We Not Need Larger Vision Models?
Model
This is a LLaVA-v1.5-13b model trained with S<sup>2</sup>-Wrapper, 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. 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 | 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 | 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.
- Task
- Text Generation
- Library
- transformers
- Type
- llava
- Created
- May 3, 2024
- Updated
- May 3, 2024