from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "broadfield-dev/gemma-3-270m-tuned-0108-1109-tuned-0108-1309"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16)
messages = [
    {"role": "system", "content": "Summarize this."},
    {"role": "user", "content": "Your input here..."}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
outputs = model.generate(inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))