hugging-face-jobs

Run GPU or CPU workloads on Hugging Face Jobs with secure token handling.

55|7|Updated Mar 2, 2026

Search Tags:#persistence #secrets #gpu #cpu #token-authentication #hugging-face-jobs #uv-scripts

Ready to run

npx skills add https://github.com/wp931120/tiny_agent --skill hugging-face-jobs-wp931120

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: hugging-face-jobs
Source: https://github.com/wp931120/tiny_agent/tree/main/workspace/skills/hugging-face-jobs
Command: npx skills add https://github.com/wp931120/tiny_agent --skill hugging-face-jobs-wp931120

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires datasets, flashinfer-python, huggingface-hub[hf_transfer], hf-xet>= 1.1.7, torch, transformers, vllm>=0.8.5, vllm>=0.6.5, 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 running workloads on Hugging Face Jobs with proper token handling and result persistence. It provides authenticated job execution, hardware flavor selection, and mechanisms to push outputs back to the Hub, ensuring ephemeral environments do not lose results.

Core Features & Use Cases

Secure token handling with secrets for HF_TOKEN
UV-script-based job submission and GPU/CPU job execution
Persistence of results to HF Hub and guidance on hardware selection and timeouts
Ready-to-run scripts and references for troubleshooting

Quick Start

Submit a GPU or CPU workload to Hugging Face Jobs using a ready-to-run UV script and push the results back 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 GPU workloads on Hugging Face Jobs and save the results?▼

You can run GPU workloads on Hugging Face Jobs using ready-to-run UV scripts, which handle secure token authentication and push output results directly back to the Hub to prevent data loss in ephemeral environments.

What is the best way to manage HF_TOKEN secrets when submitting jobs?▼

The best way to manage HF_TOKEN secrets when submitting jobs is by using secure token handling practices enforced by the skill, ensuring your authentication credentials are protected during job execution.

Does this approach support CPU and GPU hardware flavor selection for Hugging Face Jobs?▼

Yes, it supports both CPU and GPU hardware flavor selection for Hugging Face Jobs, providing guidance on choosing the appropriate hardware and managing timeouts for your specific workload requirements.

Can I use vllm and transformers to execute jobs and persist outputs to the Hub?▼

Yes, you can use vllm and transformers dependencies within your UV scripts to execute jobs and persist outputs to the Hub, leveraging end-to-end result persistence to save your computational work.

Why do my Hugging Face Jobs results disappear after execution in ephemeral environments?▼

Hugging Face Jobs results disappear in ephemeral environments because they lack end-to-end result persistence, which this skill solves by providing mechanisms to push outputs back to the Hub after execution.

What are the limitations of running UV scripts on Hugging Face Jobs?▼

While UV scripts provide ready-to-run job submission, you must consider hardware flavor selection limits and timeout constraints, and ensure proper HF_TOKEN secrets handling to avoid authentication failures during execution.