Home › Directory › Fine-tuning & Training
Fine-tuning & Training
Libraries and services for fine-tuning, training and aligning models.
JSON: /api/v1/directory.json (filter on category=fine-tuning)
Unsloth
Faster, lower-memory fine-tuning of LLMs.
FreeNo authAxolotl
Streamlined tool for fine-tuning many LLM architectures.
FreeNo authLLaMA-Factory
Unified fine-tuning of 100+ LLMs with a web UI.
FreeNo authHugging Face PEFT
Parameter-efficient fine-tuning methods.
FreeNo authHugging Face TRL
Library for SFT, DPO and RL training of language models.
FreeNo authtorchtune
PyTorch-native library for fine-tuning LLMs.
FreeNo authDeepSpeed
Distributed training and inference optimization library.
FreeNo authOpenAI Fine-tuning
Fine-tune OpenAI models through the API.
PaidAPI keyTogether AI Fine-tuning
Managed fine-tuning of open models.
PaidAPI keyFireworks Fine-tuning
Fine-tune and deploy LoRA models.
PaidAPI keyMistral Fine-tuning
Fine-tune Mistral models via API.
PaidAPI keyPredibase
Fine-tuning and serving platform for LoRA models.
PaidAPI keyOpenPipe
Distill and fine-tune models from production logs.
PaidAPI keyTinker
Thinking Machines' fine-tuning API.
PaidAPI keyOpenRLHF
Open-source RLHF framework.
FreeNo authverl
RL training library for LLMs.
FreeNo auth