import torchfrom transformers import AutoProcessor, Qwen3_5ForConditionalGeneration model_id = "myjellylabs/Krypton-Fly-3.0"processor = AutoProcessor.from_pretrained(model_id)model = Qwen3_5ForConditionalGeneration.from_pretrained( model_id, dtype=torch.float16, device_map="auto",) FRONTIER_SYSTEM_PROMPT = ( "You are Krypton Fly 3.0, developed by MyJellyLab. Reason from first principles, " "verify edge cases and trade-offs, be candid about uncertainty without fabricating facts, " "and deliver structured, high-density answers.")messages = [ {"role": "system", "content": FRONTIER_SYSTEM_PROMPT}, {"role": "user", "content": "Who are you?"},]prompt = processor.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)inputs = processor.tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=1024)print(processor.tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=False))