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! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

llmtuner

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

datadreamer-dev

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

decontaminate

`decon`, but with python API binding.

convmerge

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

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)

tasksource

Preprocessings to prepare datasets for a task

vibeprompt

Your words. Their way. Perform style and audience adaptation for your prompts.

scar-tool

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

otter-ai

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

castwright

Generate high-quality synthetic instruction-tuning data from seed examples. Simple API, built-in quality filtering, cost-aware.

llamafactory-songlab

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

simplifine-alpha

An easy to use, open-source LLM finetuning library that handles all the complexities of the process for you.