Instructions to use pfnet/Llama3-Preferred-MedSwallow-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pfnet/Llama3-Preferred-MedSwallow-70B with Transformers:

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

pipe = pipeline("text-generation", model="pfnet/Llama3-Preferred-MedSwallow-70B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pfnet/Llama3-Preferred-MedSwallow-70B")
model = AutoModelForCausalLM.from_pretrained("pfnet/Llama3-Preferred-MedSwallow-70B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pfnet/Llama3-Preferred-MedSwallow-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pfnet/Llama3-Preferred-MedSwallow-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pfnet/Llama3-Preferred-MedSwallow-70B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pfnet/Llama3-Preferred-MedSwallow-70B

SGLang

How to use pfnet/Llama3-Preferred-MedSwallow-70B 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 "pfnet/Llama3-Preferred-MedSwallow-70B" \
    --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": "pfnet/Llama3-Preferred-MedSwallow-70B",
		"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 "pfnet/Llama3-Preferred-MedSwallow-70B" \
        --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": "pfnet/Llama3-Preferred-MedSwallow-70B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pfnet/Llama3-Preferred-MedSwallow-70B with Docker Model Runner:
```
docker model run hf.co/pfnet/Llama3-Preferred-MedSwallow-70B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama3-Preferred-MedSwallow-70B

Model Description

Llama3-Preferred-MedSwallow-70B is a finetuned model based on tokyotech-llm/Llama-3-Swallow-70B-v0.1, which has undergone continued pretraining on an original corpus of medical-related text. For more details, please refer to our blog post at https://tech.preferred.jp/ja/blog/llama3-preferred-medswallow-70b/. The model is released under the META LLAMA 3 COMMUNITY LICENSE.

Model Performance

The table below shows the performance on the Japanese national medical licensing examinations from 2018 to 2022 (IgakuQA).

Model ID	Average	2018	2019	2020	2021	2022
Llama3-Preferred-MedSwallow-70B	395.2	407	390	391	393	395
GPT-4	388.8	382	385	387	398	392
Llama-3-Swallow-70B-v0.1	348.6	353	347	353	345	345
Meta-Llama-3-70B	334.6	353	340	348	314	318
Qwen2-72B	331.2	320	325	325	326	360
gemma-2-27b	316	337	298	327	296	322
Swallow-70b-NVE-hf	291.6	283	280	300	295	300
Swallow-MX-8x7b-NVE-v0.1	280.8	262	273	291	284	294
ChatGPT	273.2	266	250	266	297	287

Limitations

The model was developed for research purposes and is not intended for clinical diagnosis. It is the users' responsibility to ensure compliance with applicable rules and regulations.