Tinker
Fine-tuning API for open-weight models
Tinker is the API from Thinking Machines Lab for fine-tuning open-weight models. You write the training loop in Python, and the service runs it on managed GPU clusters.
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
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
torchtune
Fine-tuning
PyTorch-native library for fine-tuning LLMs