Instructions to use phronetic-ai/RZN-Med with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use phronetic-ai/RZN-Med with Transformers:

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

pipe = pipeline("text-generation", model="phronetic-ai/RZN-Med")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("phronetic-ai/RZN-Med")
model = AutoModelForCausalLM.from_pretrained("phronetic-ai/RZN-Med")
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 phronetic-ai/RZN-Med with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/phronetic-ai/RZN-Med

SGLang

How to use phronetic-ai/RZN-Med 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 "phronetic-ai/RZN-Med" \
    --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": "phronetic-ai/RZN-Med",
		"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 "phronetic-ai/RZN-Med" \
        --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": "phronetic-ai/RZN-Med",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use phronetic-ai/RZN-Med with Docker Model Runner:
```
docker model run hf.co/phronetic-ai/RZN-Med
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

phronetic-ai/RZN-Med

medRZN is a causal language model created for medical reasoning on open-ended questions.
⚠️ For research and educational purposes only — not for clinical use.

Disclaimer

This model is not a substitute for professional medical advice, diagnosis, or treatment. Do not use it to make clinical decisions. Always consult a licensed clinician

Load Model Directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("phronetic-ai/medRZN")
model = AutoModelForCausalLM.from_pretrained("phronetic-ai/medRZN")

Quickstart

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

modelName = "phronetic-ai/medRZN"

model = AutoModelForCausalLM.from_pretrained(
    modelName,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(modelName)

prompt = "A 45-year-old presents with chest pain. What are possible differentials?"
messages = [
    {"role": "system", "content": "You are medRZN, a medical reasoning assistant. This is not medical advice."},
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
modelInputs = tokenizer([text], return_tensors="pt").to(model.device)

generatedIds = model.generate(
    **modelInputs,
    max_new_tokens=256
)
generatedIds = [
    outputIds[len(inputIds):] for inputIds, outputIds in zip(modelInputs.input_ids, generatedIds)
]

response = tokenizer.batch_decode(generatedIds, skip_special_tokens=True)[0]
print(response)