Unsloth

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.

应用提示重复以提高非推理 LLM 的准确性

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

Guide a person in becoming a better teacher and explainer. AI coaches content structuring, audience calibration, explanation clarity, Socratic questioning technique, feedback interpretation, and reflective practice for technical presentations, documentation, and mentoring. Use when a person needs to present technical content and wants preparation coaching, wants to write better documentation or tutorials, struggles to explain concepts across expertise levels, is mentoring a colleague, or is preparing for a talk or knowledge-sharing session.