查找技能

Deploy SageMaker endpoints, the services that answer model requests, with automatic capacity scaling, CloudWatch alarms, and resource tags. Supports real-time and asynchronous inference, scaling down to zero instances, deployment checks, and resource cleanup.

中文简介正在准备中。当前显示英语简介。

• Deploying a real-time model endpoint
• Scaling a sparse workload down to zero instances
• Running long inference jobs asynchronously

Fine-tune vision models on custom images using Hugging Face Jobs cloud GPUs. Covers object detection, image classification, and segmentation—identifying image regions—with dataset validation, hardware selection, cost estimates, monitoring, and saving trained models to the Hub.

中文简介正在准备中。当前显示英语简介。

• Train an object detector on custom images
• Fine-tune an image classifier
• Adapt SAM/SAM2 to custom image masks

Write and review Gradio demos for Hugging Face ZeroGPU. Configure GPU time limits and dependencies, and troubleshoot errors caused by separate worker processes, shared state, concurrent requests, or CUDA package installation.

中文简介正在准备中。当前显示英语简介。

• Review GPU handlers in a Gradio demo
• Tune GPU duration and quota usage
• Fix PicklingError and stale state across worker processes

Manage Hugging Face Hub through the hf command line tool. Download and upload models or datasets, organize cloud storage, manage authentication and local caches, run scheduled jobs, and deploy or maintain model inference services.

中文简介正在准备中。当前显示英语简介。

• Download or publish models and datasets
• Sync training checkpoints to cloud storage
• Inspect and clean the local cache

Check the AWS profile, region, account ID, and caller identity before starting AWS work. Read local configuration and validate credentials, then flag missing settings, expired access, or possible IAM restrictions associated with SSO authentication.

中文简介正在准备中。当前显示英语简介。

• Check the AWS account and region before deployment
• Identify the active profile when none was specified
• Detect expired credentials or missing configuration

Prepare SageMaker deployments and training by finding existing execution roles, checking trust settings, and reviewing required permissions. Guides role creation only when necessary and identifies permission issues that require an AWS administrator.

中文简介正在准备中。当前显示英语简介。

• Check execution roles before deploying a SageMaker endpoint
• Find an existing role when no ARN is provided
• Investigate IAM AccessDenied errors

Estimate inference memory for models on Hugging Face Hub without downloading their weights. Check GPU capacity for Safetensors or GGUF files, with optional estimates for the KV cache, memory used to retain attention data during generation.

中文简介正在准备中。当前显示英语简介。

• Check whether a model fits on a GPU
• Compare memory estimates for GGUF quantizations
• Estimate KV cache memory for a chosen context length

Evaluate Hugging Face Hub models using inspect-ai or lighteval, with local inference or a provider-backed option. Choose an inference engine, start with a small test, and switch engines when model compatibility requires it.

中文简介正在准备中。当前显示英语简介。

• Run benchmark evaluations on a local GPU
• Choose an evaluation framework and inference engine
• Check a small sample before a full evaluation

Find and run local AI models with llama.cpp. Choose GGUF model files and quantization levels that fit available memory, launch a command line session or local server, and test an OpenAI-compatible API on your computer.

中文简介正在准备中。当前显示英语简介。

• Find models to run on a local computer
• Choose quantization for available memory
• Launch and test a local OpenAI-compatible API

Explore Hugging Face datasets through the Dataset Viewer API. Preview and retrieve rows, search text, filter records, inspect sizes and column statistics, and find Parquet download links for further analysis or data extraction.

中文简介正在准备中。当前显示英语简介。

• Preview dataset contents and data splits
• Search text and filter dataset rows
• Inspect dataset sizes, statistics, and Parquet links

Register arXiv papers on Hugging Face Hub, connect them to models and datasets, and manage authorship claims and profile visibility. Create research articles from Markdown templates and convert them into HTML for sharing.

中文简介正在准备中。当前显示英语简介。

• Registering an arXiv paper on Hugging Face Hub
• Linking papers to models and datasets
• Managing authorship claims and profile visibility

Train or fine-tune language and vision models on Hugging Face Jobs without a local GPU. Covers dataset checks, hardware and cost planning, training monitoring, Hub storage, and GGUF conversion for local use.

中文简介正在准备中。当前显示英语简介。

• Fine-tune a language model without a local GPU
• Validate preference data before DPO training
• Estimate training costs and choose GPU hardware

Keep chat-ui model settings aligned with the HuggingFace router. Add descriptions for newly available models, check reasoning support, enable artifact panels based on model size, and remove settings for models no longer served.

中文简介正在准备中。当前显示英语简介。

• Add newly released models to chat-ui settings
• Remove settings for models no longer served
• Check reasoning support and artifact eligibility

Draft huggingface_hub release notes from saved pull request JSON files. The skill groups changes, explains major updates, adds examples from documentation changes, and includes author credits and verified documentation links in a Markdown document.

中文简介正在准备中。当前显示英语简介。

• Drafting release notes from saved pull request data
• Explaining major features and breaking changes
• Adding command or API examples from documentation changes

Use when adding or migrating non-thumbnail images for a Hugging Face Blog post. Uploads body images to the Hugging Face documentation-images dataset, updates the Markdown, and verifies the new links.

中文简介正在准备中。当前显示原文说明。

Deploy an OpenEnv environment to Hugging Face Spaces. Use when asked to deploy, push to Hugging Face, or update a space.

中文简介正在准备中。当前显示原文说明。

Generate OpenEnv environments from a concrete use case (for example, "generate an env for the library textarena"). Use when asked to design or implement a new environment under envs/ by researching a target library/API, selecting matching OpenEnv examples, asking key implementation questions, and building models/client/server/openenv.yaml. Do not use for model training or evaluation tasks.

中文简介正在准备中。当前显示原文说明。

Diagnose and recover failing or stuck Hugging Face Space deployments for OpenEnv environments. Use when deploying envs from `envs/` to the Hub (`openenv` namespace with version suffixes), when Spaces are in `BUILDING`/`APP_STARTING`/`RUNTIME_ERROR`, or when release collections need to be reconciled after targeted redeploys.

中文简介正在准备中。当前显示原文说明。

Make tests pass. Invoke after /write-tests produces failing tests.

中文简介正在准备中。当前显示原文说明。

Validate changes before submitting a pull request. Run comprehensive checks including lint, tests, alignment review, and RFC analysis. Use before creating a PR, when asked if code is ready for review, or before pushing for PR.

中文简介正在准备中。当前显示原文说明。

Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.

中文简介正在准备中。当前显示原文说明。

Start work on a GitHub issue. Extracts requirements, creates worktree, sets up TDD workflow.

中文简介正在准备中。当前显示原文说明。

Work on a batch of GitHub issues in parallel using Agent Teams. Creates one worktree per issue with TDD enforcement, coordinates via a lead agent, then produces stacked PRs.

中文简介正在准备中。当前显示原文说明。

Monitor a PR's CI checks and Greptile code review after submission. Polls CI status, auto-fixes failures via ralph-loop, waits for Greptile review, addresses comments, and iterates until green.

中文简介正在准备中。当前显示原文说明。