Qlora Python Packages

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

llamafactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

soup-cli

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

airllm

AirLLM 70B inference with single 4GB GPU

backpropagate

Production-ready headless LLM fine-tuning with smart defaults, Windows support, and modular architecture

llmtuner

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

document-language-model

Document-first local LLM training, preference mining, retraining, and multi-target export from .dlm docs, codebases, and multimodal sources.

llm-forge-new

Config-driven, YAML-first open-source LLM training platform. Fine-tune language models by editing a single YAML file.

lazyllm-llamafactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

textpolicy

Reinforcement learning for text generation on MLX (Apple Silicon): GRPO/GSPO, environments, rollout, rewards, LoRA/QLoRA

llm-toolkit

Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.

easylora

Batteries-included toolkit for LoRA / QLoRA fine-tuning with Hugging Face Transformers

glmtuner

Fine-tuning ChatGLM-6B with PEFT

llamafactory-songlab

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

readme-ready

Auto-generate code documentation in Markdown format in seconds.

bitsandbytes-intel

An extension to enable performance acceleration for bitsandbytes on Intel platforms.