abetlen/llama-cpp-python

Add Finetune Support

Aperta

#814 aperta il 11 ott 2023

 (3 commenti) (8 reazioni) (0 assegnatari)Python (1442 fork)batch import
enhancementhelp wanted

Metriche repository

Star
 (10.572 stelle)
Metriche merge PR
 (Merge medio 1g 5h) (68 PR mergiate in 30 g)

Descrizione

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.

Guida contributor