unslothaiunsloth: Finetune Qwen3, Llama 4, TTS, DeepSeek

unslotUnsloth is a lhtweht tool that optimizes LLM modeling code and reduces memory usage and training time. It supports Llama and Mistral architectures and is compatible with 🤗 PEFT and TRL.Open-source Fine-tuning & Training of LLMs 🦥. Unsloth AI has 11 repositories available. Follow their code on GitHub.