Downloads · 30 days
125
1% of all-time downloads
CXR-LLAVA-v2
ECOFRI/CXR-LLAVA-v2
CXR-LLAVA-v2 is a feature extraction model from ECOFRI. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
All-time downloads
10.3K
Public
Parameters
7B
28.2 GB on disk
Likes
6
Public
Repo makeup
Click a slice to open those files.
.bin14.1 GB · 50%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- CXR-LLAVA
- Access
- Public
- Created
- Jan 12, 2024
- Updated
- Jan 18, 2024
- SHA
- b2224786
Model card
From the Hugging Face model README
CXR LLaVA
https://github.com/ECOFRI/CXR_LLaVA
Multimodal Large Language Model Fine-Tuned for Chest X-ray Images
CXR LLaVA is an innovative open-source, multimodal large language model specifically designed for generating radiologic reports from chest X-ray images.
- Arxiv Preprint Paper: Explore the detailed scientific background of CXR LLaVA on Arxiv.
- Demo Website: Experience the model in action at Radiologist App.
| Version | Input CXR resolution | Channels | Vision Encoder | Base LLM | Weight |
|---|---|---|---|---|---|
| v1.0 | 512x512 | RGB | RN50 | LLAMA2-13B-CHAT | Deprecated |
| v2.0 (Latest) | 512x512 | Grayscale | ViT-L/16 | LLAMA2-7B-CHAT | Link |
- Task
- Feature Extraction
- Library
- transformers
- Type
- CXR-LLAVA
- License
- cc-by-nc-4.0
- Created
- Jan 12, 2024
- Updated
- Jan 18, 2024