from transformers import AutoTokenizer, AutoModelForCausalLM

device = "cuda" # the device to load the model onto

# Now you do not need to add "trust_remote_code=True"
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Coder-32B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-32B-Instruct", device_map="auto").eval()

# tokenize the input into tokens

# Instead of using model.chat(), we directly use model.generate()
# But you need to use tokenizer.apply_chat_template() to format your inputs as shown below
prompt = "write a quick sort algorithm."
messages = [
    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

# Directly use generate() and tokenizer.decode() to get the output.
# Use `max_new_tokens` to control the maximum output length.
generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=2048 # can increase the output length
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(response)