Finetuning Python Packages

flaml

A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.

736K 4K 558

liger-kernel

Efficient Triton Kernels for LLM Training

582K 6K 552

qianfan

Provide best practices for LMOps, as well as elegant and convenient access to the features of the Qianfan MaaS Platform. (提供大模型工具链最佳实践，以及优雅且便捷地访问千帆大模型平台）

286K 386 61

liger-kernel-nightly

Efficient Triton Kernels for LLM Training

51K 6K 552

nemo-automodel

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

25K 677 200

soup-cli

Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.

14K 72 21

datasetrising

Toolchain for creating custom datasets and training Stable Diffusion (1.x, 2.x, XL) models and LoRAs

6K 18 1

learn2learn

A PyTorch Library for Meta-learning Research

5K 3K 359

finetuner

:dart: Task-oriented embedding tuning for BERT, CLIP, etc.

3K 2K 65

llama-recipes

This is a compatibility package to keep projects build on llama-recipes compatible with the new name llama-cookbook. If you're updating your project or starting a new one please use llama-cookbook package

3K 18K 3K

finetuning-scheduler

A PyTorch Lightning extension that accelerates and enhances foundation model experimentation with flexible fine-tuning schedules.

3K 69 8

datasety

CLI tool for dataset preparation: resize, align, caption, shuffle, synthetic, and mask generation.

2K 2 0

tapeagents

TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle

2K 319 40

phi-3-vision-mlx

Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon

2K 276 21

llmtune-local

Open-source tool (PyPI, MIT) to fine-tune LLMs and image models fully locally. Full stack solo: LoRA/QLoRA engine (PyTorch, HuggingFace PEFT/TRL, Apple Silicon/CUDA/CPU), FastAPI + React/TypeScript UI, Auth0 auth, GGUF export, CI. pip install llmtune-local

2K 0 0

fast-axolotl

High-performance Rust extensions for Axolotl (no OOM for large datasets) - drop-in acceleration for existing installations.

1K 3 0

datasetpipeline

A data processing and analysis pipeline designed to handle various jobs related to data transformation, quality assessment, deduplication, and formatting. The pipeline can be configured and executed using YAML configuration files.

1K 1 0

llama-cookbook

Llama-cookbook is a companion project to the Llama models. It's goal is to provide examples to quickly get started with fine-tuning for domain adaptation and how to run inference for the fine-tuned models.

1K 18K 3K