Fine tune with these datasets (ise-uiuc/Magicoder-OSS-Instruct-75K ise-uiuc/Magicoder-Evol-Instruct-110K)
CodeNinja-1.0-OpenChat-7B is very good model, if possible please try fine tune it with following datasets. I think , it can improve the model performance.
ise-uiuc/Magicoder-OSS-Instruct-75K
ise-uiuc/Magicoder-Evol-Instruct-110K
hey thanks for the feedback, i'm planning to release a new version soon with a dataset created by me, stay tuned 😉
This model performs well, would love to see some updates/training based on the latest C# coding models.
hey thanks for the feedback, i'm planning to release a new version soon with a dataset created by me, stay tuned 😉
waiting :)
small request, recently, Julia language 1.10 version released and brings new features. most of llama models trained data on julia 1.7 version, 1.8 version.
Please include this latest version of julia in your datasets, "https://raw.githubusercontent.com/JuliaLang/docs.julialang.org/assets/julia-1.10.0.pdf" , and https://docs.julialang.org/en/v1/, https://github.com/JuliaLang/julia.
due to this reason, no llama , deepseek models performs best for julia code generations.
Thank you.
@beowolx
It would really be nice to have Julia included along with dashboards, web apps and animation and complex math solving capabilities or deep learning models creating capabilities.