Instructions to use Henrychur/MMedS-Llama-3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Henrychur/MMedS-Llama-3-8B with Transformers:

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

pipe = pipeline("text-generation", model="Henrychur/MMedS-Llama-3-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Henrychur/MMedS-Llama-3-8B")
model = AutoModelForCausalLM.from_pretrained("Henrychur/MMedS-Llama-3-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Henrychur/MMedS-Llama-3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Henrychur/MMedS-Llama-3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Henrychur/MMedS-Llama-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Henrychur/MMedS-Llama-3-8B

SGLang

How to use Henrychur/MMedS-Llama-3-8B 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 "Henrychur/MMedS-Llama-3-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Henrychur/MMedS-Llama-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Henrychur/MMedS-Llama-3-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Henrychur/MMedS-Llama-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Henrychur/MMedS-Llama-3-8B with Docker Model Runner:
```
docker model run hf.co/Henrychur/MMedS-Llama-3-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MMedS-Llama3

💻Github Repo 🖨️arXiv Paper

The official codes for "Towards Evaluating and Building Versatile Large Language Models for Medicine"

Introduction

This repository hosts MMedS-Llama-3-8B. Its foundation model, MMed-Llama-3-8B, is a multilingual medical language model which has undergone additional continuous pretraining on MMedC. Furthermore, the model has been fine-tuned under supervision using MedS-Ins, a comprehensive dataset designed specifically for supervised fine-tuning (SFT), featuring 13.5 million samples across 122 tasks. For more details, please refer to our paper.

Usage

The model can be loaded as follows:

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Henrychur/MMed-Llama-3-8B-EnIns")
model = AutoModelForCausalLM.from_pretrained("Henrychur/MMed-Llama-3-8B-EnIns", torch_dtype=torch.float16)

Inference format is the same as Llama 3, you can check the inference code here.

Downloads last month: 1,116

Safetensors

Model size

8B params

Tensor type

F32

Model tree for Henrychur/MMedS-Llama-3-8B

Unable to build the model tree, the base model loops to the model itself. Learn more.

Datasets used to train Henrychur/MMedS-Llama-3-8B

Space using Henrychur/MMedS-Llama-3-8B 1

Paper for Henrychur/MMedS-Llama-3-8B

Towards Evaluating and Building Versatile Large Language Models for Medicine

Paper • 2408.12547 • Published Aug 22, 2024 • 1