hugging-face-model-trainer
patchy631 · Development
当用户希望使用TRL（Transformer Reinforcement Learning）在Hugging Face Jobs基础设施上训练或微调语言模型时应使用此技能。涵盖SFT、DPO、GRPO和奖励建模训练方法，以及本地部署的GGUF转换。提供TRL Jobs包、带PEP 723格式的UV脚本、数据集准备与验证、硬件选择、成本估算、Trackio监控、Hub认证和模型持久化的指导。适用于涉及云GPU训练、GGUF转换的任务，或用户提及在没有本地GPU的情况下于Hugging Face Jobs进行训练的情况。
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on 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, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
npx skills add https://github.com/patchy631/ai-engineering-hub --skill hugging-face-model-trainer
星标 35711 · 安装量 0