Instructions to use Shashwath01/Idefic_medical_VQA_merged_4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shashwath01/Idefic_medical_VQA_merged_4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="Shashwath01/Idefic_medical_VQA_merged_4bit")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Shashwath01/Idefic_medical_VQA_merged_4bit")
model = AutoModelForMultimodalLM.from_pretrained("Shashwath01/Idefic_medical_VQA_merged_4bit", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Shashwath01/Idefic_medical_VQA_merged_4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Shashwath01/Idefic_medical_VQA_merged_4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Shashwath01/Idefic_medical_VQA_merged_4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Shashwath01/Idefic_medical_VQA_merged_4bit

SGLang

How to use Shashwath01/Idefic_medical_VQA_merged_4bit 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 "Shashwath01/Idefic_medical_VQA_merged_4bit" \
    --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": "Shashwath01/Idefic_medical_VQA_merged_4bit",
		"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 "Shashwath01/Idefic_medical_VQA_merged_4bit" \
        --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": "Shashwath01/Idefic_medical_VQA_merged_4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Shashwath01/Idefic_medical_VQA_merged_4bit with Docker Model Runner:
```
docker model run hf.co/Shashwath01/Idefic_medical_VQA_merged_4bit
```

Contributed by:

Shashwath P
Shashank Ashok
Akilan Yohendiran

Total downloads all time - 2106

Model Card for Model ID

The following model is an experimental fine tuned model of the IDEFIC 9B version, for medical Visual Question Answering. It uses a dataset combined from SLAKE and VQARAD. Check the following repository for the notebooks of training,merging and inference. https://github.com/Shashwathp/Idefic_medical_vqa

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: [@Shashwath01,@Akill19,@Shashank91097 ]
Model type: [Multimodal, Visual Question Answering]
Language(s) (NLP): [English]
License: [Apache - 2.0]
Finetuned from model [optional]: [IDEFIC 9B]

Dataset

https://huggingface.co/datasets/Shashwath01/VQARAD_SLAKE

Model Sources

Repository: https://github.com/Shashwathp/Idefic_medical_vqa

How to Get Started with the Model

Check the below link to get started with inferencing. https://github.com/Shashwathp/Idefic_medical_vqa/blob/main/inference.ipynb

Downloads last month: 18

Safetensors

Model size

9B params

Tensor type

F32

F16

Inference Providers NEW

Image-Text-to-Text

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

Shashwath01
/

Idefic_medical_VQA_merged_4bit