LLaMA-Factory
Unified fine-tuning for 100+ language models
LLaMA-Factory is an open-source framework that fine-tunes many model families through a command line or a web UI. It covers supervised tuning, preference methods and quantized training.
More in Fine-tuning
Axolotl
Fine-tuning
Config-driven fine-tuning for open LLMs
Hugging Face TRL
Fine-tuning
Train language models with SFT, DPO and RL
OpenAI fine-tuning
Fine-tuning
Fine-tune OpenAI models on your own examples
Oumi
Fine-tuning
Open platform to train, evaluate and deploy models
Tinker
Fine-tuning
Fine-tuning API for open-weight models
torchtune
Fine-tuning
PyTorch-native library for fine-tuning LLMs