abetlen/llama-cpp-python

Add Finetune Support

オープン

#814 opened on 2023/10/11

 (3 件のコメント) (8 件のリアクション) (0 人の担当者)Python (1,442 件のフォーク)batch import
enhancementhelp wanted

Repository metrics

Stars
 (10,564 個のスター)
PR merge metrics
 (平均マージ 1d 5h) (30d で 68 merged PRs)

説明

In the late versions of llama.cpp there are ways to fine-tune the model using LoRA adapters: https://github.com/ggerganov/llama.cpp/pull/2632

However, either I missed it or are there no functions introduced in this PR imported into this project?

Describe alternatives you've considered Sure it's always an option to use a CLI tool, but I guess Python binding can be useful.

コントリビューターガイド