test_model.py

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

def test_model():
    base_model_name = "Qwen/Qwen2.5-0.5B-Instruct"
    adapter_path = "./qwen-codeforces-cots"

    print("Loading tokenizer...")
    tokenizer = AutoTokenizer.from_pretrained(adapter_path, trust_remote_code=True)

    print("Loading base model...")
    base_model = AutoModelForCausalLM.from_pretrained(
        base_model_name,
        dtype=torch.float32,
        trust_remote_code=True,
    )

    print("Loading fine-tuned adapter...")
    model = PeftModel.from_pretrained(base_model, adapter_path)
    model.eval()

    # Test with a simple programming problem
    test_problem = """You are given an array a of n integers. Find the maximum element in the array.

Input format:
The first line contains an integer n (1 ≤ n ≤ 100).
The second line contains n integers a₁, a₂, ..., aₙ (1 ≤ aᵢ ≤ 1000).

Output format:
Print the maximum element."""

    messages = [
        {"role": "user", "content": f"Please reason step by step about the solution, then provide a complete implementation.\n\n# Problem\n\n{test_problem}"}
    ]

    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )

    inputs = tokenizer(text, return_tensors="pt")

    print("\nGenerating response...")
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=512,
            temperature=0.7,
            do_sample=True,
            top_p=0.9,
        )

    response = tokenizer.decode(outputs[0], skip_special_tokens=True)

    print("\n" + "="*80)
    print("MODEL RESPONSE:")
    print("="*80)
    print(response)
    print("="*80)

if __name__ == "__main__":
    test_model()