Hugging Face TRL
Train language models with SFT, DPO and RL
TRL is Hugging Face's library for post-training transformer models. It provides trainers for supervised fine-tuning, preference optimization and reinforcement learning, and integrates with PEFT.
More in Fine-tuning
Axolotl
Fine-tuning
Config-driven fine-tuning for open LLMs
LLaMA-Factory
Fine-tuning
Unified fine-tuning for 100+ language models
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