app.py

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer from Hugging Face
model_name = "Qwen/Qwen2.5-Coder-32B-Instruct"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",  # Automatically selects the appropriate dtype
    device_map="auto"    # Distributes the model across available devices
)

tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the prompt for the model
prompt = "write a quick sort algorithm."

# Prepare the messages to pass to the model
messages = [
    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
    {"role": "user", "content": prompt}
]

# Generate the input for the model using the tokenizer
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Generate the response from the model
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512  # Limit the length of the generated text
)

# Decode and print the result
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)