Instruction Tuning Python Packages

llamafactory

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

bespokelabs-curator

Synthetic data curation for post-training and structured data extraction

gritlm

Generative Representational Instruction Tuning

py-data-juicer

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

datadreamer-dev

Prompt. Generate Synthetic Data. Train & Align Models.

convmerge

Merge heterogeneous chat/text sources into a single LLM training format (JSONL)

llmtuner

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

tasksource

Datasets collection and preprocessings framework for NLP extreme multitask learning

llava-torch

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

lazyllm-llamafactory

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

decontaminate

`decon`, but with python API binding.

scar-tool

[ACL 2025 main] SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models

castwright

Generate synthetic instruction-tuning data from seed examples. Simple API, built-in quality filtering, multi-provider.

otter-ai

Otter: A Multi-Modal Model with In-Context Instruction Tuning

simplifine-alpha

🚀 Easy, open-source LLM finetuning with one-line commands, seamless cloud integration, and popular optimization frameworks. ✨

vibeprompt

🦩VibePrompt. A lightweight Python package for adapting prompts by tone, style, and audience. Built on top of LangChain, VibePrompt supports multiple LLM providers and enables structured, customizable prompt transformations for developers, writers, and researchers.

llamafactory-songlab

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