SwarmMedQA-7B-v1

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "SwarmOS/SwarmMedQA-7B-v1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

messages = [
    {"role": "system", "content": "You are a clinical reasoning assistant. Provide detailed, evidence-based answers."},
    {"role": "user", "content": "What are the first-line treatments for acute STEMI?"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))