skills.rest
Bennoo
BennooCOMMUNITY
Explore all skills by this author →
𝕏@bantoutouGitHub

hugging-face-jobs

Run UV or Docker workloads on Hugging Face Jobs with hardware selection.

4|Updated Jan 12, 2026
One-click install
npx skills add https://github.com/Bennoo/classification_experience --skill hugging-face-jobs-bennoo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hugging-face-jobs
Source: https://github.com/Bennoo/classification_experience/tree/main/.claude/skills/hugging-face-jobs
Command: npx skills add https://github.com/Bennoo/classification_experience --skill hugging-face-jobs-bennoo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires datasets, flashinfer-python, huggingface-hub[hf_transfer], hf-xet>= 1.1.7, torch, transformers, vllm>=0.8.5, numpy, tqdm, scikit-learn, polars>=1.31.0, ascii-graph, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill enables users to run any workload on Hugging Face Jobs infrastructure, eliminating local setup hurdles by leveraging UV scripts, Docker-based runs, and managed hardware.

Core Features & Use Cases

  • Managed compute on HF Jobs: Execute data processing, batch inference, experiments, and model training on cloud GPUs/CPUs without local GPUs.
  • Secure credentials & persistence: Provide HF_TOKEN via secrets, persist results to the Hub or external storage, and monitor job status.
  • Hardware & timeouts: Choose from a range of hardware flavors (CPU/GPU/TPU), configure timeouts, and monitor progress to control costs.
  • Use Case: Rapidly run a large inference job on HF Jobs and push artifacts back to a dataset on the Hub for reproducibility.

Quick Start

To run a simple UV job on CPU-basic flavor, submit a script inline or via URL to HF Jobs using the provided MCP tool. For example, run a small Python snippet and ensure HF_TOKEN is supplied via secrets so logs and outputs persist to the Hub.

Frequently Asked Questions about hugging-face-jobs

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run batch inference workloads on Hugging Face Jobs without a local GPU?▼

You can execute batch inference on Hugging Face Jobs by submitting UV scripts or Docker-based workloads to managed cloud hardware. This approach bypasses local GPU requirements by leveraging Hugging Face infrastructure for compute tasks.

How do I securely manage my HF_TOKEN when running Docker-based jobs on Hugging Face?▼

Secure token handling for Docker-based jobs is managed by providing your HF_TOKEN via secrets management. This enforces secure credential configuration while ensuring logs and outputs persist correctly to the Hub during workload execution.

Can I select specific hardware flavors and configure timeouts for compute tasks on Hugging Face Jobs?▼

Yes, you can select from a range of hardware flavors including CPU, GPU, and TPU when running compute tasks on Hugging Face Jobs. You can also configure timeouts and monitor progress to effectively control your infrastructure costs.

What is the best way to persist results from a Hugging Face Job back to the Hub?▼

The best way to persist results is to enforce Hub persistence by pushing artifacts back to a dataset on the Hub. This ensures reproducibility and secure storage of your outputs after executing data processing or model training workloads.

Does Hugging Face Jobs support running workloads using UV scripts and Python dependencies like transformers and vllm?▼

Yes, Hugging Face Jobs supports running workloads via UV scripts and utilizes Python dependencies such as transformers, vllm, and datasets. This allows you to execute data processing and inference tasks directly in the cloud environment.

Related Skills

cpich3gcpich3g

hugging-face-jobs

Run UV scripts or Docker jobs on Hugging Face Jobs with HF_TOKEN.

Community
Advanced
xjtu-wangxjtu-wang
4

report-delivery

Export chat results and long content as Markdown or PDF reports.

Community
Intermediate
pelcherspelchers

using-huggingface

Connect HuggingFace models, datasets, and spaces for ML workflows.

Community
Advanced
keremtoker468-dotcomkeremtoker468-dotcom

hf-jobs

Execute Python scripts or Docker images on Hugging Face cloud infrastructure.

Community
Advanced