
Run local evals on Hugging Face models with inspect-ai or lighteval and pick a backend
- Open source
- 11.4K GitHub stars
- AI models and LLM tooling

Run local evals on Hugging Face models with inspect-ai or lighteval and pick a backend

Explore Hugging Face datasets through the read-only Dataset Viewer API

Build Gradio web UIs, chatbots and ML demos in Python, and call Spaces from the CLI

Fine-tune LLMs with TRL or Unsloth on Hugging Face Jobs GPUs and convert to GGUF

Find GGUF models on Hugging Face, pick a quant and serve them locally with llama.cpp

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA

Publish and manage research papers on Hugging Face Hub

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/dataset

Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loadi

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help

Track and visualize ML training experiments with Trackio

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3,

AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex

Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex

Call the Gemini API from the shell with gemini-api

Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation,

Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/

Use this skill for generative video editing, text-to-video, image- and video-referenced video generation, first-frame-to-video, first-and-la

Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer),

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matche

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy Tensor

Component-owned guidance for CDF Simulation requests submitted directly or through Airflow-triggered DIG Flow Catalog prompts — golden THT b

Grade or filter workflow HDF5 episodes with an OpenAI-compatible vision model

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin.

Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents

Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders)

Generates llms.txt and llms-full.txt files for LLM-friendly project documentation following the llms.txt specification

Use this skill when a user wants to create, run, or analyze evaluation suites for Microsoft 365 Copilot declarative agents with the public @