Downloads · 30 days
24
2% of all-time downloads
LLaVA-vicuna-7B-v1.3-ScienceQA
ChangyuanWang/LLaVA-vicuna-7B-v1.3-ScienceQA
LLaVA-vicuna-7B-v1.3-ScienceQA is a machine learning model from ChangyuanWang. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Efficient and accurate memory saving method towards W4A4 large multi-modal models. [Paper][Code]
All-time downloads
1.2K
Public
Repo size
28.2 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin14.1 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- llava
- Access
- Public
- Created
- Jan 3, 2025
- Updated
- Jan 4, 2025
- SHA
- a4b4b543
Model card
From the Hugging Face model README
[NeurIPS'24]Q-VLM: Post-training Quantization for Large Vision-Language Models
Efficient and accurate memory saving method towards W4A4 large multi-modal models. [Paper][Code]
Q-VLM: Post-training Quantization for Large Vision-Language Models
Changyuan Wang, Ziwei Wang, Xiuwei Xu, Yansong Tang, Jie Zhou, Jiwen Lu
Finetuning LLaVA Model on ScienceQA Dataset
Thanks for LLaVA (https://github.com/haotian-liu/LLaVA) for the amazing open-source model!
We combined the LLaVA-7B-v1.1 model (LLaVA-7B-v1.1) and the projector from LLaVA-7B-v1.3 (LLaVA-7B-v1.3 projector) and finetuned the model on the ScienceQA dataset. This model is used to test the effectiveness of our quantization method on the ScienceQA dataset.
- Type
- llava
- License
- apache-2.0
- Created
- Jan 3, 2025
- Updated
- Jan 4, 2025