Med-CXRGen
Collection
[ACL 2024] 🔬Visual Instruction-tuned Adaptation for Chest X-ray Report Generation (Glasgow AI4BioMed Lab @ BioNLP 2024) • 6 items • Updated • 1
Image-Text-to-Text
Transformers
PyTorch
Safetensors
libra
text-generation
RRG
Radiology Report Generation
Chest X-ray
Multimodal Large Language Models
Automated Chest X-ray Report Generation
How to use from
SGLangUse Docker images
docker run --gpus all \
--shm-size 32g \
-p 30000:30000 \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_TOKEN=<secret>" \
--ipc=host \
lmsysorg/sglang:latest \
python3 -m sglang.launch_server \
--model-path "X-iZhang/Med-CXRGen-I" \
--host 0.0.0.0 \
--port 30000# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "X-iZhang/Med-CXRGen-I",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
Med-CXRGen-I Model Card
Task: Radiology Report Generation – Impression section (RRG Shared Task)
Paper and Resources
For details on Med-CXRGen-I, including its architecture, training strategy, and evaluation—please refer to the following resources:
- 📘 Paper: Gla-AI4BioMed at RRG24: Visual Instruction-tuned Adaptation for Radiology Report Generation
- 💻 Code Repository: GitHub: Med-CXRGen
How to Cite ✒️
If you use this model in academic or research contexts, please cite:
@inproceedings{zhang-etal-2024-gla,
title = "Gla-{AI}4{B}io{M}ed at {RRG}24: Visual Instruction-tuned Adaptation for Radiology Report Generation",
author = "Zhang, Xi and
Meng, Zaiqiao and
Lever, Jake and
Ho, Edmond S.L.",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Miwa, Makoto and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "Proceedings of the 23rd Workshop on Biomedical Natural Language Processing",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.bionlp-1.54/",
doi = "10.18653/v1/2024.bionlp-1.54",
pages = "624--634",
}
- Downloads last month
- 16
Model tree for X-iZhang/Med-CXRGen-I
Base model
liuhaotian/llava-v1.5-7b
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "X-iZhang/Med-CXRGen-I" \ --host 0.0.0.0 \ --port 30000# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "X-iZhang/Med-CXRGen-I", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'