🎩 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets.

Updated 1 year ago

1 year ago

8007de06f5d9 · 3.8GB

model

archllama

parameters6.74B

quantizationQ4_0

3.8GB

template

{{ .System }} @@ Instruction {{ .Prompt }} @@ Response

57B

system

You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliab

134B

params

{ "num_ctx": 16384 }

18B

Readme

🎩

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.

References

GitHub

HuggingFace