Instructions to use johnsnowlabs/JSL-MedMX-7X with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use johnsnowlabs/JSL-MedMX-7X with Transformers:

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

pipe = pipeline("text-generation", model="johnsnowlabs/JSL-MedMX-7X")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("johnsnowlabs/JSL-MedMX-7X")
model = AutoModelForCausalLM.from_pretrained("johnsnowlabs/JSL-MedMX-7X")
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 johnsnowlabs/JSL-MedMX-7X with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "johnsnowlabs/JSL-MedMX-7X"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "johnsnowlabs/JSL-MedMX-7X",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/johnsnowlabs/JSL-MedMX-7X

SGLang

How to use johnsnowlabs/JSL-MedMX-7X 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 "johnsnowlabs/JSL-MedMX-7X" \
    --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": "johnsnowlabs/JSL-MedMX-7X",
		"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 "johnsnowlabs/JSL-MedMX-7X" \
        --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": "johnsnowlabs/JSL-MedMX-7X",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use johnsnowlabs/JSL-MedMX-7X with Docker Model Runner:
```
docker model run hf.co/johnsnowlabs/JSL-MedMX-7X
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

JSL-MedMX-7X

This model is developed by John Snow Labs. Performance on biomedical benchmarks: Open Medical LLM Leaderboard.

This model is available under a CC-BY-NC-ND license and must also conform to this Acceptable Use Policy. If you need to license this model for commercial use, please contact us at info@johnsnowlabs.com.

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "johnsnowlabs/JSL-MedMX-7X"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

🏆 Evaluation

Tasks	Version	Filter	Metric	Value		Stderr
stem	N/A	none	acc_norm	0.5783	±	0.0067
		none	acc	0.6177	±	0.0057
- medmcqa	Yaml	none	acc	0.5668	±	0.0077
		none	acc_norm	0.5668	±	0.0077
- medqa_4options	Yaml	none	acc	0.6159	±	0.0136
		none	acc_norm	0.6159	±	0.0136
- anatomy (mmlu)	0	none	acc	0.7111	±	0.0392
- clinical_knowledge (mmlu)	0	none	acc	0.7396	±	0.0270
- college_biology (mmlu)	0	none	acc	0.7778	±	0.0348
- college_medicine (mmlu)	0	none	acc	0.6647	±	0.0360
- medical_genetics (mmlu)	0	none	acc	0.7200	±	0.0451
- professional_medicine (mmlu)	0	none	acc	0.7868	±	0.0249
- pubmedqa	1	none	acc	0.7840	±	0.0184

Downloads last month: 11

Safetensors

Model size

7B params

Tensor type

F16

Model tree for johnsnowlabs/JSL-MedMX-7X

Quantizations

1 model

johnsnowlabs
/

JSL-MedMX-7X

JSL-MedMX-7X

💻 Usage

🏆 Evaluation

Model tree for johnsnowlabs/JSL-MedMX-7X

Space using johnsnowlabs/JSL-MedMX-7X 1