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

python

from transformers import AutoTokenizer, AutoModelForCausalLM

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

Quickstart

python

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)