Why I use it: Fine-tune LLMs 2-5x faster with 80% less memory. The speed demon of LLM training.
Why I use it: The most popular LLM application framework. Chains, agents, RAG, and tools for building AI apps.
Why I use it: Fine-tune GPT models on your data. The easiest path to custom LLMs for specific use cases.
Why I use it: Claude API with 200K context, tool use, and advanced reasoning. The thinking model for complex tasks.
Why I use it: Run open-source LLMs locally with one command. Privacy-first, free, and incredibly simple.
Why I use it: The most popular open-source LLM fine-tuning tool. LoRA, QLoRA, and full fine-tuning via YAML config.