Quantization made by Richard Erkhov.

EditCoder-6.7b-v1 - GGUF

Model creator: https://huggingface.co/nuprl/
Original model: https://huggingface.co/nuprl/EditCoder-6.7b-v1/

Name	Quant method	Size
EditCoder-6.7b-v1.Q2_K.gguf	Q2_K	2.36GB
EditCoder-6.7b-v1.Q3_K_S.gguf	Q3_K_S	2.75GB
EditCoder-6.7b-v1.Q3_K.gguf	Q3_K	3.07GB
EditCoder-6.7b-v1.Q3_K_M.gguf	Q3_K_M	3.07GB
EditCoder-6.7b-v1.Q3_K_L.gguf	Q3_K_L	3.35GB
EditCoder-6.7b-v1.IQ4_XS.gguf	IQ4_XS	3.4GB
EditCoder-6.7b-v1.Q4_0.gguf	Q4_0	3.56GB
EditCoder-6.7b-v1.IQ4_NL.gguf	IQ4_NL	3.59GB
EditCoder-6.7b-v1.Q4_K_S.gguf	Q4_K_S	3.59GB
EditCoder-6.7b-v1.Q4_K.gguf	Q4_K	3.8GB
EditCoder-6.7b-v1.Q4_K_M.gguf	Q4_K_M	3.8GB
EditCoder-6.7b-v1.Q4_1.gguf	Q4_1	3.95GB
EditCoder-6.7b-v1.Q5_0.gguf	Q5_0	4.33GB
EditCoder-6.7b-v1.Q5_K_S.gguf	Q5_K_S	4.33GB
EditCoder-6.7b-v1.Q5_K.gguf	Q5_K	4.46GB
EditCoder-6.7b-v1.Q5_K_M.gguf	Q5_K_M	4.46GB
EditCoder-6.7b-v1.Q5_1.gguf	Q5_1	4.72GB
EditCoder-6.7b-v1.Q6_K.gguf	Q6_K	5.15GB
EditCoder-6.7b-v1.Q8_0.gguf	Q8_0	6.67GB

Original model description:

language: - code datasets: - nuprl/EditPackFT library_name: transformers pipeline_tag: text2text-generation tags: - code model-index: - name: EditCoder-6.7b-v1 results: - task: type: text-generation dataset: type: nuprl/CanItEdit name: CanItEdit Descriptive metrics: - name: pass@1 type: pass@1 value: 0.4815 verified: false - task: type: text-generation dataset: type: nuprl/CanItEdit name: CanItEdit Lazy metrics: - name: pass@1 type: pass@1 value: 0.3696 verified: false

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.