ai-forever / ai-forever/mgpt

Fine-tunning with specific words for non english language

未關閉
#8 0 則留言 0 個 reaction 已指派 0 人 在 GitHub 檢視
主要語言
Jupyter Notebook
星號
204
分支
23
PR 合併指標
30 天內沒有已合併 PR

描述

Hi

Is it possible to finetune the LLM (mgpt) with specific words?
I want the model to answer with just few available words in my dictionary not all the possible words for specific languages (I'm talking about Persian Language)

My dictionary of words {around 2000} are in CVS or text file!

would it be possible to do this? if yes, would you please guide me through?

Thanks
Best regards

貢獻指南

這個儲存庫沒有索引到貢獻指南

評估

這個 Issue 還沒有評估資料。

把新 issue 寄到你的電子郵件信箱

精選適合新手參與的 GitHub issue 摘要。