Instructions to use foundationmodels/MIMIC-medical-report with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use foundationmodels/MIMIC-medical-report with Transformers:

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

pipe = pipeline("text-generation", model="foundationmodels/MIMIC-medical-report", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("foundationmodels/MIMIC-medical-report", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use foundationmodels/MIMIC-medical-report with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/foundationmodels/MIMIC-medical-report

SGLang

How to use foundationmodels/MIMIC-medical-report 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 "foundationmodels/MIMIC-medical-report" \
    --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": "foundationmodels/MIMIC-medical-report",
		"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 "foundationmodels/MIMIC-medical-report" \
        --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": "foundationmodels/MIMIC-medical-report",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use foundationmodels/MIMIC-medical-report with Docker Model Runner:
```
docker model run hf.co/foundationmodels/MIMIC-medical-report
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

MIMIC-Medical-Report Model

Overview

This project presents a fine-tuned model based on Microsoft's PHI-2, trained on the MIMIC dataset using Python and PyTorch. Leveraging Hugging Face's Transformers library, this model significantly enhances AI's capacity to extract critical medical insights, improving diagnostic accuracy in healthcare.

Features

Model Architecture: Fine-tuned PHI-2 model using Transformer-based architecture
Dataset: MIMIC medical dataset, preprocessed to ensure high data integrity
Purpose: Assists in generating detailed medical reports, extracting key insights to support clinical decisions

Downloads last month: 4

Safetensors

Model size

3B params

Tensor type

F16