EditCoder-6.7b (version 1) is a fine-tuned version of DeepSeek Coder (base model, 6.7b parameters) for instructional code editing. We utilize EditPackFT as our fine-tuning dataset, and we show state-of-the-art performance among non-distilled open source models for code editing, using the CanItEdit benchmark.
More information can be found on our paper. NOTE: This is the model trained on EditPackFT, not Commits2023FT. We are working on releasing that one soon.
Citation
If you use our work, please cite our paper as such:
@inproceedings{cassano2023edit,
title={{Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions}},
author={Federico Cassano and Luisa Li and Akul Sethi and Noah Shinn and Abby Brennan-Jones and Anton Lozhkov and Carolyn Jane Anderson and Arjun Guha},
booktitle={The First International Workshop on Large Language Model for Code},
year={2024},
url={https://arxiv.org/abs/2312.12450}
}
Prompt
The model has been trained on the following prompt format:
## Code Before:
{before}
## Instruction:
{instruction}
## Code After:
{after}
Here is a python function that can be used for formatting the prompt correctly:
def edit_prompt(old, instr):
before = f"""## Code Before:\n{old}\n"""
instr = f"""## Instruction:\n{instr}\n"""
after = f"""## Code After:\n"""
return before + instr + after
Train Your Own EditCoder
We provide the full pipeline that was used for training our own edit-coder model. The pipeline and instructions can be found on our GitHub repository.
- Downloads last month
- 27
Dataset used to train nuprl/EditCoder-6.7b-v1
Collection including nuprl/EditCoder-6.7b-v1
Evaluation results
- pass@1 on CanItEdit Descriptiveself-reported0.481
- pass@1 on CanItEdit Lazyself-reported0.370