使用 TRL（Transformer 强化学习）或 Unsloth 结合 Hugging Face Jobs 基础设施，训练或微调语言和视觉模型。涵盖 SFT、DPO、GRPO 和奖励建模训练方法，以及用于本地部署的 GGUF 转换。
该技能旨在帮助开发者利用 Hugging Face 的云 GPU 作业（Jobs）基础设施，高效地训练或微调大型语言模型（LLM）和视觉模型。它支持多种先进的训练方法，包括监督微调（SFT）、直接偏好优化（DPO）、基于组相对策略优化（GRPO）以及奖励建模。技能不仅提供了使用 TRL 和 Unsloth 库的详细指引，还涵盖了从数据集准备、验证到硬件选择、成本估算和模型监控的完整工作流程。此外，它还包含了将训练好的模型转换为 GGUF 格式以进行本地部署的指导。该技能适用于任何需要在无本地 GPU 情况下进行云端训练、微调或模型转换的场景。
npx skills add https://github.com/huggingface/skills/tree/main/skills/huggingface-llm-trainerInstalled? Explore more 编程与开发 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
使用 TRL（Transformer 强化学习）或 Unsloth 结合 Hugging Face Jobs 基础设施，训练或微调语言和视觉模型。涵盖 SFT、DPO、GRPO 和奖励建模训练方法，以及用于本地部署的 GGUF 转换。包括对 TRL Jobs 包、采用 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 身份验证、模型选择/排行榜及模型持久化的指导。适用于涉及云 GPU 训练、GGUF 转换，或当用户提到在没有本地 GPU 设置的情况下在 Hugging Face Jobs 上训练的任务。
This repo contains 5 individual skills — each has its own dedicated page.
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.
Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.
Send and manage iMessages via BlueBubbles, including attachments, tapbacks, edits, replies, and groups.
Control Eight Sleep pods (status, temperature, alarms, schedules).
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Create, search, and manage Bear notes via grizzly CLI.
Capture frames or clips from RTSP/ONVIF cameras.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.