skills.rest
pingqLIN
pingqLINCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

hugging-face-evaluation

Extract README evaluation tables and import Artificial Analysis benchmarks into Hugging Face model cards.

Updated Mar 24, 2026
Search Tags:#automation#evaluation#benchmark#huggingface#readme-extraction#model-card
One-click install
npx skills add https://github.com/pingqLIN/UniText --skill hugging-face-evaluation-pingqlin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hugging-face-evaluation
Source: https://github.com/pingqLIN/UniText/tree/main/runtime/skills/hugging-face-evaluation
Command: npx skills add https://github.com/pingqLIN/UniText --skill hugging-face-evaluation-pingqlin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires huggingface_hub, markdown-it-py, python-dotenv, pyyaml, requests, inspect-ai, inspect-evals, openai, lighteval, vllm, torch, transformers, accelerate, and includes scripts (resource) components.

What problem does it solve?

This skill helps teams publish and maintain up-to-date evaluation results by linking README-based benchmarks, automated imports from Artificial Analysis, and model-index updates for Hugging Face model cards.

Core Features & Use Cases

  • Extract evaluation tables from a model's README and convert them into model-index metrics.
  • Import benchmark scores from the Artificial Analysis API and merge them with existing evaluations.
  • Run end-to-end evaluations using vLLM or lighteval and push updates to HF model cards via pull requests.
  • Supports multiple workflows: readme extraction, AA imports, and PR-based updates to model cards.

Quick Start

To attach evaluation results to HF model cards, run the integrated README extraction and AA import workflow to produce a model-index payload.

Frequently Asked Questions about hugging-face-evaluation

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

FAQPage Schema
How do I attach evaluation results to Hugging Face model cards automatically?▼

To attach evaluation results to Hugging Face model cards, this skill extracts benchmark tables from README files and imports scores from Artificial Analysis, then pushes updates to model cards via pull requests using authenticated tokens.

Can I import Artificial Analysis benchmark scores into my Hugging Face model card?▼

Yes, you can import Artificial Analysis benchmark scores by providing your AA_API_KEY. The skill fetches scores from the Artificial Analysis API and merges them with existing model-index metrics on your Hugging Face model card.

How do I extract evaluation tables from a Hugging Face README into model-index metrics?▼

Extracting evaluation tables from a Hugging Face README uses the integrated extraction workflow to parse markdown table structures and convert them into standardized model-index metrics for your model card.

Do I need HF_TOKEN and AA_API_KEY to update Hugging Face model cards with benchmarks?▼

Yes, HF_TOKEN and AA_API_KEY are required to update Hugging Face model cards with benchmarks. These tokens enforce safe operations by authenticating pull request updates and Artificial Analysis API imports before validating table structures.

Can I run end-to-end model evaluations with vLLM or lighteval and push results to Hugging Face?▼

Yes, you can run end-to-end model evaluations with vLLM or lighteval and push results to Hugging Face. The skill executes the evaluation and automatically submits pull requests to update your model card with the new benchmark data.

What is the best way to keep Hugging Face model card benchmarks up to date in a registry-driven workflow?▼

The best way to keep Hugging Face model card benchmarks up to date is linking README extraction, Artificial Analysis imports, and automated PR updates. This workflow parses existing tables and merges new scores to maintain accurate model-index metadata.

Related Skills

Explore More Data & Analytics Skills→
POWERFULMOVESPOWERFULMOVES
1

hugging-face-evaluation-manager

Extract evaluation tables from READMEs and import benchmark scores from the Artificial Analysis API.

Community
Advanced
ISAQQSAIISAQQSAI

hugging-face-evaluation-manager

Automate evaluation result updates in Hugging Face model cards.

Community
Advanced
huggingfacehuggingface
10.9k

hugging-face-evaluation

Convert README evaluation tables into Hugging Face model-index format.

Official
Advanced
patronus-aipatronus-ai
2

hugging-face-evaluation-manager

Extract README evaluation tables into model-index YAML for Hugging Face model cards.

Official
Advanced