from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig

model_name = "frankdarkluo/DeepSeek-R1-Distill-Qwen-32B-GPTQ-Int8"

tokenizer = AutoTokenizer.from_pretrained(model_name)
quantized_model = AutoModelForCausalLM.from_pretrained(model_name, device_map='cuda')

chat = [{"role": "user", "content": "Why is grass green?"},]
question_tokens = tokenizer.apply_chat_template(chat, add_generation_prompt=True, return_tensors="pt").to(quantized_model.device)
answer_tokens = quantized_model.generate(question_tokens, generation_config=GenerationConfig(max_length=2048, ))[0]

print(tokenizer.decode(answer_tokens))