Instructions to use umarigan/blip-image-captioning-base-chestxray-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use umarigan/blip-image-captioning-base-chestxray-finetuned with Transformers:

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

pipe = pipeline("image-text-to-text", model="umarigan/blip-image-captioning-base-chestxray-finetuned")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("umarigan/blip-image-captioning-base-chestxray-finetuned")
model = AutoModelForImageTextToText.from_pretrained("umarigan/blip-image-captioning-base-chestxray-finetuned")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use umarigan/blip-image-captioning-base-chestxray-finetuned with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/umarigan/blip-image-captioning-base-chestxray-finetuned

SGLang

How to use umarigan/blip-image-captioning-base-chestxray-finetuned 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 "umarigan/blip-image-captioning-base-chestxray-finetuned" \
    --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": "umarigan/blip-image-captioning-base-chestxray-finetuned",
		"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 "umarigan/blip-image-captioning-base-chestxray-finetuned" \
        --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": "umarigan/blip-image-captioning-base-chestxray-finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use umarigan/blip-image-captioning-base-chestxray-finetuned with Docker Model Runner:
```
docker model run hf.co/umarigan/blip-image-captioning-base-chestxray-finetuned
```

Model Card for Model ID

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: Umar Igan
Model type: VLM
Language(s) (NLP): English
License: [More Information Needed]
Finetuned from model [optional]: Salesforce/blip-image-captioning-base

Model Sources [optional]

Repository: [More Information Needed]

Uses

This is a fine-tuned VLM on chest xray medicald dataset, the result shouldn't be used as an advice!!

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Example usage:

from transformers import BlipForConditionalGeneration, AutoProcessor

model = BlipForConditionalGeneration.from_pretrained("umarigan/blip-image-captioning-base-chestxray-finetuned").to(device)
processor = AutoProcessor.from_pretrained("umarigan/blip-image-captioning-base-chestxray-finetuned")

inputs = processor(images=image, return_tensors="pt").to(device)
pixel_values = inputs.pixel_values

generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(generated_caption)

Training Data

https://huggingface.co/datasets/Shrey-1329/cxiu_hf_dataset

Training Hyperparameters

lr: 5e-5
Epoch: 10
Dataset size: 1k

Summary

A simple blip fine-tuned model on medical imaging

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: GPU
Hours used: 1
Cloud Provider: Google
Compute Region: Frankfurt
Carbon Emitted:

Compute Infrastructure

Google Colab L4 GPU

Hardware

Google Colab L4 GPU

Model Card Contact

Umar Igan

Downloads last month: 36

Safetensors

Model size

0.2B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Space using umarigan/blip-image-captioning-base-chestxray-finetuned 1

Paper for umarigan/blip-image-captioning-base-chestxray-finetuned

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 47