abetlen/llama-cpp-python

Add Finetune Support

Open

#814 opened on Oct 11, 2023

View on GitHub
 (3 comments) (8 reactions) (0 assignees)Python (644 forks)batch import
enhancementhelp wanted

Repository metrics

Stars
 (4,995 stars)
PR merge metrics
 (Avg merge 1d 5h) (68 merged PRs in 30d)

Description

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.

Contributor guide

Research direction
Review the referenced PR (llama.cpp #2632) to understand the new LoRA API, then examine the existing Python bindings in llama cpp python to determine how to expose the fine tuning functions, likely via ctypes or cffi. Check for any existing work in progress branches or discussions.
Tech stack
python
Domain
machine learningapi
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonC++ basics (for binding)
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40