Huggingface Skills
by @huggingface · plugin · 25 skills
Huggingface Skills from huggingface/skills.
Install the whole plugin (CLI)
npx skillmds add huggingface/hf-cli
npx skillmds add huggingface/hf-mem
npx skillmds add huggingface/trl-training
npx skillmds add huggingface/huggingface-best
npx skillmds add huggingface/transformers-js
npx skillmds add huggingface/huggingface-papers
npx skillmds add huggingface/huggingface-spaces
npx skillmds add huggingface/huggingface-gradio
npx skillmds add huggingface/huggingface-zerogpu
npx skillmds add huggingface/huggingface-datasets
npx skillmds add huggingface/huggingface-local-models
npx skillmds add huggingface/huggingface-trackio
npx skillmds add huggingface/huggingface-tool-builder
npx skillmds add huggingface/hf-cloud-python-env-setup
npx skillmds add huggingface/huggingface-vision-trainer
npx skillmds add huggingface/huggingface-llm-trainer
npx skillmds add huggingface/huggingface-community-evals
npx skillmds add huggingface/huggingface-paper-publisher
npx skillmds add huggingface/train-sentence-transformers
npx skillmds add huggingface/hf-cloud-aws-context-discovery
npx skillmds add huggingface/huggingface-lora-space-builder
npx skillmds add huggingface/hf-cloud-sagemaker-iam-preflight
npx skillmds add huggingface/hf-cloud-serving-image-selection
npx skillmds add huggingface/hf-cloud-sagemaker-deployment-planner
npx skillmds add huggingface/hf-cloud-sagemaker-production-defaultsSkills in this plugin
- ▌ hf-cli · huggingfaceManage Hugging Face Hub resources: download/upload models, datasets, spaces; manage repos, buckets, collections, discussions, and cache; run SQL queries on datasets; authenticate and manage tokens.
- ▌ hf-mem · huggingfaceEstimates the memory required to load Safetensors or GGUF model weights for inference from the Hugging Face Hub, using HTTP Range requests without downloading weights.
- ▌ trl-training · huggingfaceTrain and fine-tune transformer language models using TRL (Transformers Reinforcement Learning) with support for SFT, DPO, GRPO, KTO, RLOO, and reward model training via CLI commands.
- ▌ huggingface-best · huggingfaceQueries Hugging Face benchmark leaderboards to find the best AI models for a task, filters by device constraints, and returns a ranked comparison table with scores.
- ▌ transformers-js · huggingface bundleRun state-of-the-art machine learning models directly in JavaScript/TypeScript across browsers and server-side runtimes using Transformers.js.
- ▌ huggingface-papers · huggingfaceLook 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.
- ▌ huggingface-spaces · huggingface bundleCreate, deploy, and debug machine learning applications on Hugging Face Spaces using Gradio, Docker, or Static SDKs, with support for ZeroGPU and dedicated hardware.
- ▌ huggingface-gradio · huggingface bundleBuild interactive web UIs and ML demos in Python using Gradio's core API, components, and patterns.
- ▌ huggingface-zerogpu · huggingface bundleBuild ML demos on Hugging Face Spaces with ZeroGPU hardware, covering @spaces.GPU decorator usage, duration and quota tuning, process isolation, CUDA availability model, concurrency safety, and build constraints.
- ▌ huggingface-datasets · huggingfaceFetch dataset metadata, paginate rows, search text, apply filters, and download parquet URLs from the Hugging Face Dataset Viewer API.
- ▌ huggingface-local-models · huggingface bundleSearch the Hugging Face Hub for llama.cpp-compatible GGUF models, select the right quantization, and run them locally with llama-cli or llama-server.
- ▌ huggingface-trackio · huggingface bundleTrack and visualize ML training experiments with Trackio, including logging metrics, firing alerts, and retrieving data via CLI. Supports real-time dashboards, webhook alerts, and HF Space syncing.
- ▌ huggingface-tool-builder · huggingface bundleCreates reusable command-line scripts and utilities for the Hugging Face API, enabling chaining, piping, and intermediate data processing.
- ▌ hf-cloud-python-env-setup · huggingface bundleSets up an isolated Python environment for SageMaker and AWS work, pinning Python version and installing current boto3/awscli to avoid dependency conflicts and stale SDKs.
- ▌ huggingface-vision-trainer · huggingface bundleTrains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.
- ▌ huggingface-llm-trainer · huggingface bundleTrain or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs cloud infrastructure, with support for SFT, DPO, GRPO, and reward modeling, plus GGUF conversion for local deployment.
- ▌ huggingface-community-evals · huggingface bundleRun evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware, with backend selection between vLLM, Transformers, and accelerate.
- ▌ huggingface-paper-publisher · huggingface bundlePublish and manage research papers on Hugging Face Hub, including creating paper pages, linking papers to models and datasets, claiming authorship, and generating professional markdown-based research articles.
- ▌ train-sentence-transformers · huggingface bundleTrain or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.
- ▌ hf-cloud-aws-context-discovery · huggingfaceReads the local AWS configuration to determine the active profile, region, account ID, and caller identity before any AWS task, avoiding guesswork and preventing common deployment errors.
- ▌ huggingface-lora-space-builder · huggingface bundleBuild and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA, including picking the right base pipeline, designing a tailored UI, and publishing the Space.
- ▌ hf-cloud-sagemaker-iam-preflight · huggingface bundleDiscovers, validates, or creates a SageMaker execution role before deploying or training, preventing IAM-related deployment failures.
- ▌ hf-cloud-serving-image-selection · huggingface bundleSelects the correct SageMaker serving container image URI for HuggingFace model deployments, prioritizing HuggingFace-curated Deep Learning Containers over generic alternatives.
- ▌ hf-cloud-sagemaker-deployment-planner · huggingfacePlans and coordinates the deployment of a model to Amazon SageMaker AI, selecting the appropriate pathway (real-time, serverless, async, batch, or Bedrock CMI) based on model type, traffic, latency, and cost constraints.
- ▌ hf-cloud-sagemaker-production-defaults · huggingface bundleCreates SageMaker endpoints (real-time or async) with autoscaling, CloudWatch alarms, and tagging enabled by default, then smoke-tests them before declaring success.