Update README.md
Browse files
README.md
CHANGED
|
@@ -5,12 +5,26 @@ base_model:
|
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
---
|
| 7 |
|
| 8 |
-
# CodeLlama-13b-MORepair
|
| 9 |
-
|
| 10 |
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.
|
| 11 |
|
| 12 |
[Paper](https://arxiv.org/abs/2404.12636) | [Code](https://github.com/buaabarty/morepair)
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
## Model Description
|
| 15 |
|
| 16 |
- **Base Model**: CodeLlama-13b-instruct
|
|
@@ -134,22 +148,4 @@ print(fixed_code)
|
|
| 134 |
- **Context Window**: Same as CodeLlama-13b-instruct
|
| 135 |
- **Input Format**: Code snippets with optional repair guidance
|
| 136 |
|
| 137 |
-
## Citation
|
| 138 |
-
|
| 139 |
-
If you use this model in your research, please cite:
|
| 140 |
-
```bibtex
|
| 141 |
-
@article{10.1145/3735129,
|
| 142 |
-
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},
|
| 143 |
-
title = {MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning},
|
| 144 |
-
year = {2025},
|
| 145 |
-
publisher = {Association for Computing Machinery},
|
| 146 |
-
issn = {1049-331X},
|
| 147 |
-
url = {https://doi.org/10.1145/3735129},
|
| 148 |
-
doi = {10.1145/3735129},
|
| 149 |
-
journal = {ACM Trans. Softw. Eng. Methodol.},
|
| 150 |
-
}
|
| 151 |
-
```
|
| 152 |
-
|
| 153 |
-
## Acknowledgments
|
| 154 |
|
| 155 |
-
This model builds upon the CodeLlama model family developed by Meta AI and incorporates the MOREPAIR framework for enhanced program repair capabilities.
|
|
|
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
---
|
| 7 |
|
|
|
|
|
|
|
| 8 |
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.
|
| 9 |
|
| 10 |
[Paper](https://arxiv.org/abs/2404.12636) | [Code](https://github.com/buaabarty/morepair)
|
| 11 |
|
| 12 |
+
## Citation
|
| 13 |
+
|
| 14 |
+
If you use this model in your research, please cite:
|
| 15 |
+
```bibtex
|
| 16 |
+
@article{10.1145/3735129,
|
| 17 |
+
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},
|
| 18 |
+
title = {MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning},
|
| 19 |
+
year = {2025},
|
| 20 |
+
publisher = {Association for Computing Machinery},
|
| 21 |
+
issn = {1049-331X},
|
| 22 |
+
url = {https://doi.org/10.1145/3735129},
|
| 23 |
+
doi = {10.1145/3735129},
|
| 24 |
+
journal = {ACM Trans. Softw. Eng. Methodol.},
|
| 25 |
+
}
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
## Model Description
|
| 29 |
|
| 30 |
- **Base Model**: CodeLlama-13b-instruct
|
|
|
|
| 148 |
- **Context Window**: Same as CodeLlama-13b-instruct
|
| 149 |
- **Input Format**: Code snippets with optional repair guidance
|
| 150 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 151 |
|
|
|