README.md

metadata

license: llama2
base_model:
  - codellama/CodeLlama-13b-Instruct-hf
pipeline_tag: text-generation

CodeLlama-13b-MORepair is a program repair model fine-tuned from CodeLlama-13b-instruct using a novel multi-objective fine-tuning framework called MOREPAIR. This model is specifically designed to improve automated program repair capabilities by learning both code transformations and repair logic reasoning.

Paper | Code | Colab

Citation

If you use this model in your research, please cite:

@article{10.1145/3735129,
author = {Yang, Boyang and Tian, Haoye and Ren, Jiadong and Zhang, Hongyu and Klein, Jacques and Bissyande, Tegawende and Le Goues, Claire and Jin, Shunfu},
title = {MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning},
year = {2025},
publisher = {Association for Computing Machinery},
issn = {1049-331X},
url = {https://doi.org/10.1145/3735129},
doi = {10.1145/3735129},
journal = {ACM Trans. Softw. Eng. Methodol.},
}

Model Description

• Base Model: CodeLlama-13b-instruct
• Training Technique: Multi-objective fine-tuning with MOREPAIR framework
• Supported Languages: Primarily tested on C++ and Java, but likely generalizes to other languages
• Primary Use: Automated program repair
• License: Llama 2 Community License
• Evaluation Benchmarks: EvalRepair-Java | EvalRepair-C++ | D4J-Repair | SWE-Repair

Training Details

Training Data

• Dataset: TutorLLMCode
• Size: 1,535 pairs of buggy and repaired code
• Nature: Programming task corrections with LLM-generated repair guidance

Training Approach

The model was trained using MOREPAIR, which employs:

• Multi-objective learning with two objectives:
  1. Generating repaired code
  2. Producing repaired code with explanatory guidance
• QLoRA fine-tuning (only 1.84% of parameters modified)
• NEFTune for improved generalization
• LLM-generated guidance for understanding repair logic

Usage

Here's how to use the model with the Hugging Face Transformers library:

Installation

pip install transformers torch

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

# Load model and tokenizer
model_name = "barty/CodeLlama-13B-MORepair"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    load_in_8bit=True,
    torch_dtype=torch.float16
)
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

def repair_code(buggy_code, filename="example.java"):
    # Construct prompt in the format model expects
    prompt = f"""[INST] This is an incorrect code({filename}):
```java
{buggy_code}
```
You are a software engineer. Can you repair the incorrect code?
[/INST]
```java
"""
    
    # Calculate token count for length control
    prompt_tokens = len(tokenizer.tokenize(prompt))
    max_new_tokens = 500 - prompt_tokens
    
    # Generate repair
    output = pipe(
        prompt,
        min_length=prompt_tokens + 64,
        max_length=prompt_tokens + max_new_tokens,
        temperature=1.0,
        do_sample=True
    )
    
    # Extract the generated code
    full_text = output[0]['generated_text']
    fixed_code = full_text.split('[/INST]')[1].strip()
    
    return full_text, fixed_code

# Example usage
buggy_code = """
public static int findMinRotated(int[] arr) {
    int left = 0;
    int right = arr.length - 1;
    
    while (left < right) {
        int mid = (left + right) / 2;
        if (arr[mid] > arr[right])
            left = mid;  // Bug: should be mid + 1
        else
            right = mid;
    }
    return arr[left];
}
"""

full_response, fixed_code = repair_code(buggy_code)
print("Fixed code:")
print(fixed_code)

Important Parameters

• load_in_8bit=True: Enables 8-bit quantization for efficient inference
• temperature=1.0: Controls randomness in generation
• do_sample=True: Enables sampling-based generation
• min_length: Minimum length of generated text
• max_length: Maximum length of generated text

Limitations

• Performance varies across different programming languages
• May require multiple attempts to generate correct fixes
• Should be used with appropriate test cases to validate repairs
• May not handle very complex or multi-file program repairs

Technical Specifications

• Architecture: Based on CodeLlama-13b-instruct
• Parameters: Same as base model (13B)
• Fine-tuning Method: QLoRA + NEFTune
• Context Window: Same as CodeLlama-13b-instruct
• Input Format: Code snippets with optional repair guidance