Code-Optimizer

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

# 1. Configuration
base_model_id = "Qwen/Qwen2.5-Coder-7B-Instruct"
adapter_repo_id = "SeifElden2342532/Code-Optimizer"

# 2. Load Tokenizer and Base Model
tokenizer = AutoTokenizer.from_pretrained(base_model_id)
model = AutoModelForCausalLM.from_pretrained(
    base_model_id, 
    torch_dtype=torch.bfloat16, 
    device_map="auto"
)

# 3. Load and Merge the LoRA Adapter
model = PeftModel.from_pretrained(model, adapter_repo_id)
model = model.merge_and_unload() # Merging for faster inference

# 4. Prepare the Input
messages = [
    {
        "role": "system", 
        "content": "You are an expert Python code optimizer. Your goal is to take user-provided Python code and optimize it for performance, readability, or conciseness, based on the user's specified category. Provide the optimized code, a brief explanation of the changes, and a complexity comparison table (e.g., time and space complexity before and after optimization)."
    },
    {
        "role": "user", 
        "content": "Original Code:\n