Name	Quant method	Size
Magicoder-S-DS-6.7B.Q2_K.gguf	Q2_K	2.36GB
Magicoder-S-DS-6.7B.IQ3_XS.gguf	IQ3_XS	2.61GB
Magicoder-S-DS-6.7B.IQ3_S.gguf	IQ3_S	2.75GB
Magicoder-S-DS-6.7B.Q3_K_S.gguf	Q3_K_S	2.75GB
Magicoder-S-DS-6.7B.IQ3_M.gguf	IQ3_M	2.9GB
Magicoder-S-DS-6.7B.Q3_K.gguf	Q3_K	3.07GB
Magicoder-S-DS-6.7B.Q3_K_M.gguf	Q3_K_M	3.07GB
Magicoder-S-DS-6.7B.Q3_K_L.gguf	Q3_K_L	3.35GB
Magicoder-S-DS-6.7B.IQ4_XS.gguf	IQ4_XS	3.4GB
Magicoder-S-DS-6.7B.Q4_0.gguf	Q4_0	3.56GB
Magicoder-S-DS-6.7B.IQ4_NL.gguf	IQ4_NL	3.59GB
Magicoder-S-DS-6.7B.Q4_K_S.gguf	Q4_K_S	3.59GB
Magicoder-S-DS-6.7B.Q4_K.gguf	Q4_K	3.8GB
Magicoder-S-DS-6.7B.Q4_K_M.gguf	Q4_K_M	3.8GB
Magicoder-S-DS-6.7B.Q4_1.gguf	Q4_1	3.95GB
Magicoder-S-DS-6.7B.Q5_0.gguf	Q5_0	4.33GB
Magicoder-S-DS-6.7B.Q5_K_S.gguf	Q5_K_S	4.33GB
Magicoder-S-DS-6.7B.Q5_K.gguf	Q5_K	4.46GB
Magicoder-S-DS-6.7B.Q5_K_M.gguf	Q5_K_M	4.46GB
Magicoder-S-DS-6.7B.Q5_1.gguf	Q5_1	4.72GB
Magicoder-S-DS-6.7B.Q6_K.gguf	Q6_K	5.15GB

Original model description:

license: other library_name: transformers datasets:

ise-uiuc/Magicoder-OSS-Instruct-75K
ise-uiuc/Magicoder-Evol-Instruct-110K license_name: deepseek pipeline_tag: text-generation

🎩 Magicoder: Source Code Is All You Need

Refer to our GitHub repo ise-uiuc/magicoder for an up-to-date introduction to the Magicoder family!

🎩Magicoder is a model family empowered by 🪄OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets for generating low-bias and high-quality instruction data for code.
🪄OSS-Instruct mitigates the inherent bias of the LLM-synthesized instruction data by empowering them with a wealth of open-source references to produce more diverse, realistic, and controllable data.

Model Details

Model Description

Developed by: Yuxiang Wei, Zhe Wang, Jiawei Liu, Yifeng Ding, Lingming Zhang
License: DeepSeek
Finetuned from model: deepseek-coder-6.7b-base

Model Sources

Repository: https://github.com/ise-uiuc/magicoder
Paper: https://arxiv.org/abs/2312.02120
Demo (powered by Gradio): https://github.com/ise-uiuc/magicoder/tree/main/demo

Training Data

Magicoder-OSS-Instruct-75K: generated through OSS-Instruct using gpt-3.5-turbo-1106 and used to train both Magicoder and Magicoder-S series.
Magicoder-Evol-Instruct-110K: decontaminated and redistributed from theblackcat102/evol-codealpaca-v1, used to further finetune Magicoder series and obtain Magicoder-S models.

Uses

Direct Use

Magicoders are designed and best suited for coding tasks.

Out-of-Scope Use

Magicoders may not work well in non-coding tasks.

Bias, Risks, and Limitations

Magicoders may sometimes make errors, producing misleading contents, or struggle to manage tasks that are not related to coding.

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

How to Get Started with the Model

Use the code below to get started with the model. Make sure you installed the transformers library.

python

from transformers import pipeline
import torch

MAGICODER_PROMPT = """You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.

@@ Instruction
{instruction}

@@ Response
"""

instruction = <Your code instruction here>

prompt = MAGICODER_PROMPT.format(instruction=instruction)
generator = pipeline(
    model="ise-uiuc/Magicoder-S-DS-6.7B",
    task="text-generation",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
result = generator(prompt, max_length=1024, num_return_sequences=1, temperature=0.0)
print(result[0]["generated_text"])

Technical Details

Refer to our GitHub repo: ise-uiuc/magicoder.

Citation

bibtex

@misc{magicoder,
    title={Magicoder: Source Code Is All You Need}, 
    author={Yuxiang Wei and Zhe Wang and Jiawei Liu and Yifeng Ding and Lingming Zhang},
    year={2023},
    eprint={2312.02120},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

Acknowledgements

WizardCoder: Evol-Instruct
DeepSeek-Coder: Base model for Magicoder-DS
CodeLlama: Base model for Magicoder-CL
StarCoder: Data decontamination

Important Note

Magicoder models are trained on the synthetic data generated by OpenAI models. Please pay attention to OpenAI's terms of use when using the models and the datasets. Magicoders will not compete with OpenAI's commercial products.

RichardErkhov/ise-uiuc_-_Magicoder-S-DS-6.7B-gguf