from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "zhangsq-nju/Qwen3-0.6B-EdgeRazor-1.58bit"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False # For EdgeRazor-nbit, we only train the instruct mode.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 151668 ()
    index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")

print("thinking content:", thinking_content)
print("content:", content)

@article{zhangsh-edgerazor,
  title={{EdgeRazor}: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation},
  author={Shu-Hao Zhang and Le-Tong Huang and Xiang-Sheng Deng and Xin-Yi Zou and Chen Wu and Nan Li and Shao-Qun Zhang},
  year={2026},
}