Instructions to use thaiphonghuan/BLIP-finetuned-chest-xray-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thaiphonghuan/BLIP-finetuned-chest-xray-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="thaiphonghuan/BLIP-finetuned-chest-xray-v1")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("thaiphonghuan/BLIP-finetuned-chest-xray-v1")
model = AutoModelForImageTextToText.from_pretrained("thaiphonghuan/BLIP-finetuned-chest-xray-v1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thaiphonghuan/BLIP-finetuned-chest-xray-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thaiphonghuan/BLIP-finetuned-chest-xray-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thaiphonghuan/BLIP-finetuned-chest-xray-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/thaiphonghuan/BLIP-finetuned-chest-xray-v1

SGLang

How to use thaiphonghuan/BLIP-finetuned-chest-xray-v1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "thaiphonghuan/BLIP-finetuned-chest-xray-v1" \
    --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": "thaiphonghuan/BLIP-finetuned-chest-xray-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use 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 "thaiphonghuan/BLIP-finetuned-chest-xray-v1" \
        --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": "thaiphonghuan/BLIP-finetuned-chest-xray-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use thaiphonghuan/BLIP-finetuned-chest-xray-v1 with Docker Model Runner:
```
docker model run hf.co/thaiphonghuan/BLIP-finetuned-chest-xray-v1
```

BLIP-finetuned-chest-xray-v1 / README.md

thaiphonghuan

Update README.md

21bcc71 verified 5 months ago

preview code

raw

history blame contribute delete

1.83 kB

metadata

license: apache-2.0
tags:
  - vision-language
  - image-captioning
  - medical-imaging
  - chest-xray
  - blip
  - finetuned
library_name: transformers

Fine-tuned BLIP on Chest X-rays (Indiana University)

This repository contains a fine-tuned BLIP (Bootstrapped Language-Image Pretraining) model trained on the Chest X-rays (Indiana University) dataset.
The model is adapted for vision–language tasks in the medical imaging domain, particularly chest X-ray understanding.

🧠 Model Description

Base model: BLIP (Bootstrapped Language-Image Pretraining)
Fine-tuning domain: Medical imaging
Modality: Vision–Language (Image + Text)
Target data: Chest X-ray images (frontal & lateral views)

The goal of fine-tuning is to adapt BLIP to better capture radiological visual patterns and associated semantic information from chest X-ray images.

📊 Dataset Information

The model is fine-tuned using the Chest X-rays (Indiana University) dataset.

Dataset Source

Kaggle:
https://www.kaggle.com/datasets/raddar/chest-xrays-indiana-university

Image Preprocessing Pipeline

Original images were provided in raw DICOM format. Each image was converted to PNG with the following preprocessing steps:

Outlier clipping
- The top and bottom 0.5% of DICOM pixel values were clipped
- Purpose: eliminate extremely dark or bright pixel outliers
Intensity normalization
- DICOM pixel values were linearly scaled to the 0–255 range
Resizing
- Images were resized so that the shorter side is 2048 pixels
- This was done to comply with Kaggle dataset size limits
View classification
- Each image was manually classified into:
  - Frontal chest X-ray
  - Lateral chest X-ray