đ đŠ Magicoder: Source Code Is All You Need
Magicoder is a model family empowered by OSS - Instruct, a novel approach that uses open - source code snippets to generate low - bias and high - quality instruction data for code, enabling more diverse and controllable data generation.
đ Quick Start
Use the code below to get started with the model. Make sure you installed the transformers library.
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-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"])
⨠Features
- đŠMagicoder is a model family empowered by đĒOSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets for generating low-bias and high-quality instruction data for code.
- đĒOSS-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.

đ Documentation
Model Details
Model Description
Model Sources
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.
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.
đ§ Technical Details
Refer to our GitHub repo: ise-uiuc/magicoder.
đ License
The model is under the DeepSeek license.
đ Citation
@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}
}
đ Acknowledgements
â ī¸ 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.