The AI community building the future.
Hugging Face publishes skills that help AI agents post-train language models with TRL, including SFT, DPO, GRPO, and reward-model training, and track those experiments with Trackio. Its skills also cover deploying models to SageMaker by choosing serving images and preparing execution roles, building Gradio web UIs, training sentence-transformers embedding and reranker models, and querying the Hugging Face Hub through MCP. Taken together, the skills span the full model lifecycle, from training and evaluation to deployment and the Hub tooling that connects them.
Skills
26 skills · 11,289 stars · Apache-2.0
Hf Cli Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, bu…
Hf Cloud Aws Context Discovery Discover the user's local AWS context (active profile, region, account ID, caller identity) at th…
Hf Cloud Python Env Setup Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and…
Hf Cloud Sagemaker Deployment Planner Plan and coordinate the deployment of a model to Amazon SageMaker AI.
Hf Cloud Sagemaker Iam Preflight Ensure a usable SageMaker execution role exists before deploying or training.
Hf Cloud Sagemaker Production Defaults Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, Clou…
Hf Cloud Serving Image Selection Pick the right serving container for a SageMaker model deployment and find its current image URI.
Hf Mcp Use Hugging Face Hub via MCP server tools.
Hf Mem Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for in…
Huggingface Best Use when the user asks about finding the best, top, or recommended model for a task, wants to kno…
Huggingface Community Evals Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware.
Huggingface Datasets Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, pa…
Huggingface Gradio Build Gradio web UIs and demos in Python.
Huggingface Llm Trainer Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or U…
Huggingface Local Models Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm.
Huggingface Lora Space Builder Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA.
Huggingface Paper Publisher Publish and manage research papers on Hugging Face Hub.
Huggingface Papers Look up and read Hugging Face paper pages in markdown, and use the papers API for structured meta…
Huggingface Spaces Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs,…
Huggingface Tool Builder Use this skill when the user wants to build tool/scripts or achieve a task where using data from…
Huggingface Trackio Track and visualize ML training experiments with Trackio.
Huggingface Vision Trainer Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image…
Huggingface Zerogpu AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU.
Train Sentence Transformers Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense o…
Transformers Js Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeSc…
Trl Training Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-…