SwarmMed-7B-v5-merged

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "SwarmOS/SwarmMed-7B-v5-merged"
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."},
    {"role": "user", "content": "Explain the mechanism of action of metformin in type 2 diabetes."}
]

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))