Instructions to use mlpipes-asabay/md-assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlpipes-asabay/md-assistant with Transformers:

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

pipe = pipeline("text-generation", model="mlpipes-asabay/md-assistant")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlpipes-asabay/md-assistant")
model = AutoModelForCausalLM.from_pretrained("mlpipes-asabay/md-assistant", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mlpipes-asabay/md-assistant with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mlpipes-asabay/md-assistant

SGLang

How to use mlpipes-asabay/md-assistant 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 "mlpipes-asabay/md-assistant" \
    --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": "mlpipes-asabay/md-assistant",
		"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 "mlpipes-asabay/md-assistant" \
        --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": "mlpipes-asabay/md-assistant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mlpipes-asabay/md-assistant with Docker Model Runner:
```
docker model run hf.co/mlpipes-asabay/md-assistant
```

MD-Assistant

MD-Assistant is a fine-tuned llama-2-13B-chat-hf model on the medical_dialog dataset. This model is experimental and is a possible building block for AI assisted tools in clinical visit application use cases, where it might be the core component of an AI tool to assist clinicians.

What makes MedDialog dataset particularly interesting for fine-tuning an llm like the llama-2 is its scope and diversity. The dataset contains over 250,000 utterances from both patients and doctors, spanning 51 different medical categories and 96 specialties. This wealth of information provides a unique opportunity for machine learning models to learn patterns and relationships within medical dialogues, which can ultimately enhance decision-making processes in healthcare settings.

This dataset can be found here on Hugging Face as medical_dialog.

Important:

This conversational AI model is not intended to provide medical advice or diagnose medical conditions. It is solely designed to assist with generating hypothetical patient scenarios for educational purposes. Any information provided by this model should not be considered medical advice or substitute for professional medical judgment. If you have any health concerns or symptoms, we strongly encourage you to seek advice from a qualified healthcare professional. Only licensed physicians and medical professionals are trained and authorized to provide medical advice and treatment. Use of this model does not establish a doctor-patient relationship. We disclaim any warranty or liability for damages resulting from the use of this model, including but not limited to direct, indirect, incidental, punitive, and consequential damages.

Downloads last month: 10

Safetensors

Model size

13B params

Tensor type

F32

F16