New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Hugging Face Local Model Evals

by huggingface in huggingface/skills

Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.

OfficialApache-2.0Auto-check passedAI & LLM Engineering

Install Hugging Face Local Model Evals

skills CLI
$ npx skills add huggingface/skills --skill huggingface-community-evals -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install huggingface/skills huggingface-community-evals --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/huggingface/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/huggingface-community-evals .claude/skills/huggingface-community-evals && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
huggingface-community-evals
GitHub stars
11k
Used in
2 other repos
Token cost
~1.6k tokens
SKILL.md length
681 words
Files
6 (incl. scripts)
Skills in repo
25
Repo updated
First seen
Licence
Apache-2.0

At a glance

Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.

  • Works in 5 steps: Choose the evaluation framework. → Choose the inference backend. → Start with a smoke test. → …
  • Evaluating a Hub model locally with inspect-ai or lighteval
  • SKILL.md covers Option A: inspect-ai with…, Option B: inspect-ai on Local… and Option C: lighteval on Local GPU
  • Runs Python scripts from its folder; calls uv; needs HF_TOKEN

What it does

The skill covers running model evaluations locally against models on the Hugging Face Hub, using either inspect-ai or lighteval. Three bundled scripts handle the common cases: inspect_eval_uv.py for provider-backed inspect-ai runs, inspect_vllm_uv.py for local GPU runs with vLLM or Transformers, and lighteval_vllm_uv.py for lighteval with vLLM or accelerate. A usage examples file adds more command patterns.

The workflow picks a framework, then a backend, preferring vLLM for throughput and keeping Transformers or accelerate as compatibility fallbacks. It starts with a smoke test limited to 10 samples and scales up only after that passes. Prerequisites are uv, an HF_TOKEN for gated or private models and a working nvidia-smi for GPU runs. Remote runs on Hugging Face Jobs, model-card edits and publishing evaluation results are out of scope and are handed to other skills.

When your agent uses it

  • Evaluating a Hub model locally with inspect-ai or lighteval
  • Choosing between vLLM, Transformers and accelerate for a local eval
  • Running a quick smoke test before a full benchmark run

Example prompts

  • “Run a lighteval smoke test of my model on the local GPU with vLLM.”
  • “Evaluate this Hub model with inspect-ai through an inference provider.”
  • “Should I use vLLM or accelerate to evaluate a model on my workstation GPU?”

Requirements

  • uv for running the scripts
  • An HF_TOKEN for gated or private models
  • An NVIDIA GPU with nvidia-smi for local GPU runs

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Choose the evaluation framework.
  2. Choose the inference backend.
  3. Start with a smoke test.
  4. Scale up only after the smoke test passes.
  5. If the user wants remote execution, hand off to hugging-face-jobs with the same script + args.

What it can do on your machine

Read from SKILL.md and the folder at commit c3ff942. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 3 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • HF_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hugging Face Local Model Evals loads about 1.6k tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 681 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from huggingface/skills at commit c3ff942, republished under its Apache-2.0 licence (© huggingface). 681 words, ~1,638 tokens.

Download SKILL.mdSave it as .claude/skills/huggingface-community-evals/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
huggingface-community-evals
description
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.

Overview

This skill is for running evaluations against models on the Hugging Face Hub on local hardware.

It covers:

  • inspect-ai with local inference
  • lighteval with local inference
  • choosing between vllm, Hugging Face Transformers, and accelerate
  • smoke tests, task selection, and backend fallback strategy

It does not cover:

  • Hugging Face Jobs orchestration
  • model-card or model-index edits
  • README table extraction
  • Artificial Analysis imports
  • .eval_results generation or publishing
  • PR creation or community-evals automation

If the user wants to run the same eval remotely on Hugging Face Jobs, hand off to the hugging-face-jobs skill and pass it one of the local scripts in this skill.

If the user wants to publish results into the community evals workflow, stop after generating the evaluation run and hand off that publishing step to ~/code/community-evals.

All paths below are relative to the directory containing this SKILL.md.

When To Use Which Script

Use caseScript
Local inspect-ai eval on a Hub model via inference providersscripts/inspect_eval_uv.py
Local GPU eval with inspect-ai using vllm or Transformersscripts/inspect_vllm_uv.py
Local GPU eval with lighteval using vllm or acceleratescripts/lighteval_vllm_uv.py
Extra command patternsexamples/USAGE_EXAMPLES.md

Prerequisites

  • Prefer uv run for local execution.
  • Set HF_TOKEN for gated/private models.
  • For local GPU runs, verify GPU access before starting:
bash
uv --version
printenv HF_TOKEN >/dev/null
nvidia-smi

If nvidia-smi is unavailable, either:

  • use scripts/inspect_eval_uv.py for lighter provider-backed evaluation, or
  • hand off to the hugging-face-jobs skill if the user wants remote compute.

Core Workflow

  1. Choose the evaluation framework.
    • Use inspect-ai when you want explicit task control and inspect-native flows.
    • Use lighteval when the benchmark is naturally expressed as a lighteval task string, especially leaderboard-style tasks.
  2. Choose the inference backend.
    • Prefer vllm for throughput on supported architectures.
    • Use Hugging Face Transformers (--backend hf) or accelerate as compatibility fallbacks.
  3. Start with a smoke test.
    • inspect-ai: add --limit 10 or similar.
    • lighteval: add --max-samples 10.
  4. Scale up only after the smoke test passes.
  5. If the user wants remote execution, hand off to hugging-face-jobs with the same script + args.

Quick Start

Option A: inspect-ai with local inference providers path

Best when the model is already supported by Hugging Face Inference Providers and you want the lowest local setup overhead.

bash
uv run scripts/inspect_eval_uv.py \
  --model meta-llama/Llama-3.2-1B \
  --task mmlu \
  --limit 20

Use this path when:

  • you want a quick local smoke test
  • you do not need direct GPU control
  • the task already exists in inspect-evals

Option B: inspect-ai on Local GPU

Best when you need to load the Hub model directly, use vllm, or fall back to Transformers for unsupported architectures.

Local GPU:

bash
uv run scripts/inspect_vllm_uv.py \
  --model meta-llama/Llama-3.2-1B \
  --task gsm8k \
  --limit 20

Transformers fallback:

bash
uv run scripts/inspect_vllm_uv.py \
  --model microsoft/phi-2 \
  --task mmlu \
  --backend hf \
  --trust-remote-code \
  --limit 20
Show full SKILL.md (273 more words)Show less

Option C: lighteval on Local GPU

Best when the task is naturally expressed as a lighteval task string, especially Open LLM Leaderboard style benchmarks.

Local GPU:

bash
uv run scripts/lighteval_vllm_uv.py \
  --model meta-llama/Llama-3.2-3B-Instruct \
  --tasks "leaderboard|mmlu|5,leaderboard|gsm8k|5" \
  --max-samples 20 \
  --use-chat-template

accelerate fallback:

bash
uv run scripts/lighteval_vllm_uv.py \
  --model microsoft/phi-2 \
  --tasks "leaderboard|mmlu|5" \
  --backend accelerate \
  --trust-remote-code \
  --max-samples 20

Remote Execution Boundary

This skill intentionally stops at local execution and backend selection.

If the user wants to:

  • run these scripts on Hugging Face Jobs
  • pick remote hardware
  • pass secrets to remote jobs
  • schedule recurring runs
  • inspect / cancel / monitor jobs

then switch to the hugging-face-jobs skill and pass it one of these scripts plus the chosen arguments.

Task Selection

inspect-ai examples:

  • mmlu
  • gsm8k
  • hellaswag
  • arc_challenge
  • truthfulqa
  • winogrande
  • humaneval

lighteval task strings use suite|task|num_fewshot:

  • leaderboard|mmlu|5
  • leaderboard|gsm8k|5
  • leaderboard|arc_challenge|25
  • lighteval|hellaswag|0

Multiple lighteval tasks can be comma-separated in --tasks.

Backend Selection

  • Prefer inspect_vllm_uv.py --backend vllm for fast GPU inference on supported architectures.
  • Use inspect_vllm_uv.py --backend hf when vllm does not support the model.
  • Prefer lighteval_vllm_uv.py --backend vllm for throughput on supported models.
  • Use lighteval_vllm_uv.py --backend accelerate as the compatibility fallback.
  • Use inspect_eval_uv.py when Inference Providers already cover the model and you do not need direct GPU control.

Hardware Guidance

Model sizeSuggested local hardware
< 3Bconsumer GPU / Apple Silicon / small dev GPU
3B - 13Bstronger local GPU
13B+high-memory local GPU or hand off to hugging-face-jobs

For smoke tests, prefer cheaper local runs plus --limit or --max-samples.

Troubleshooting

  • CUDA or vLLM OOM:
    • reduce --batch-size
    • reduce --gpu-memory-utilization
    • switch to a smaller model for the smoke test
    • if necessary, hand off to hugging-face-jobs
  • Model unsupported by vllm:
    • switch to --backend hf for inspect-ai
    • switch to --backend accelerate for lighteval
  • Gated/private repo access fails:
    • verify HF_TOKEN
  • Custom model code required:
    • add --trust-remote-code

Examples

See:

  • examples/USAGE_EXAMPLES.md for local command patterns
  • scripts/inspect_eval_uv.py
  • scripts/inspect_vllm_uv.py
  • scripts/lighteval_vllm_uv.py

© huggingface, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts) in skills/huggingface-community-evals of huggingface/skills.

  • SKILL.md
  • examples/.env.example
  • examples/USAGE_EXAMPLES.md
  • scripts/inspect_eval_uv.py
  • scripts/inspect_vllm_uv.py
  • scripts/lighteval_vllm_uv.py

Open the folder on GitHubat commit c3ff942

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in huggingface/skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Hugging Face Local Model Evals next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hugging Face Local Model Evals compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hugging Face Local Model Evals this skillhuggingface/skills11k2 repos~1.6kAutomated safety check: PassApache-2.0
Hugging Face Community Evalssickn33/agentic-awesome-skills47k1 repos~1.9kAutomated safety check: PassApache-2.0
bitsandbytes Model QuantizationOrchestra-Research/AI-Research-SKILLs13k2 repos~2.5kAutomated safety check: PassMIT
Open Weightsericrisco/rsc-harness174—~4.1kAutomated safety check: PassMIT
LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs13k8 repos~3kAutomated safety check: PassMIT
Ascend Model Adapter for vLLMvllm-project/vllm-ascend2.9k—~2.2kAutomated safety check: PassApache-2.0

Similar skills

  • Hugging Face Community Evals

    sickn33/agentic-awesome-skills

    Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware.

    47k GitHub starsUsed in 1 repo~1.9k tokens
    AI & LLM EngineeringAuto-check passed

  • bitsandbytes Model Quantization

    Orchestra-Research/AI-Research-SKILLs

    Loads large language models in 8-bit or 4-bit with bitsandbytes so they fit smaller GPUs, and sets up QLoRA fine-tuning on a 4-bit base model.

    13k GitHub starsUsed in 2 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed

  • Open Weights

    ericrisco/rsc-harness

    A skill your agent uses when choosing an open-weight LLM and clearing it for use — which family and size fit the task, the hardware and the budget, and above all whether the license permits shipping.

    174 GitHub stars~4.1k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • LLM Benchmarking with lm-evaluation-harness

    Orchestra-Research/AI-Research-SKILLs

    Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.

    13k GitHub starsUsed in 8 repos~3k tokens
    AI & LLM EngineeringAuto-check passed

  • Ascend Model Adapter for vLLM

    vllm-project/vllm-ascend

    Adapts and debugs Hugging Face or local models to run on vLLM with Ascend NPU, validates them by serving, and delivers the result as one signed commit.

    2.9k GitHub stars~2.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Add Model

    guoqingbao/xinfer

    Adapt and port new LLM model architectures to this xinfer project.

    334 GitHub stars~4.2k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check: notes

More from huggingface/skills

All 25 skills in this repo

  • SageMaker IAM Role Preflight

    huggingface/skills

    Official

    Finds or validates a usable SageMaker execution role before deploying or training, so scripts do not try to create IAM roles they lack permission to create.

    11k GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed

  • SageMaker Serving Image Selection

    huggingface/skills

    Official

    Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

    11k GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed

  • Sentence-Transformers Training Router

    huggingface/skills

    Official

    Routes a sentence-transformers training task to the right model type and required reference docs and example scripts, covering bi-encoders, rerankers, sparse and multi-vector models.

    11k GitHub starsUsed in 1 repo~2.6k tokens
    Auto-check passed

  • Python Environment Setup for SageMaker

    huggingface/skills

    Official

    Sets up an isolated Python environment with a supported interpreter and current boto3 before any SageMaker deployment, training or AWS automation code runs.

    11k GitHub starsUsed in 2 repos~1.7k tokens
    Auto-check passed

  • SageMaker Production Defaults

    huggingface/skills

    Official

    Deploys SageMaker endpoints with autoscaling, CloudWatch alarms and tags on by default, using scripts for real-time, scale-to-zero and async setups.

    11k GitHub starsUsed in 1 repo~6.9k tokens
    Auto-check passed

  • Hugging Face Paper Publisher

    huggingface/skills

    Official

    Indexes research papers on the Hugging Face Hub from arXiv, links them to models and datasets, claims authorship and generates markdown research articles from templates.

    11k GitHub starsUsed in 4 repos~4.2k tokens
    Auto-check passed

Works with

Categories

Questions about Hugging Face Local Model Evals

What does Hugging Face Local Model Evals do?

Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends. The skill covers running model evaluations locally against models on the Hugging Face Hub, using either inspect-ai or lighteval.py for lighteval with vLLM or accelerate.

When should I use Hugging Face Local Model Evals?

Hugging Face Local Model Evals fits situations like: evaluating a Hub model locally with inspect-ai or lighteval; choosing between vLLM, Transformers and accelerate for a local eval; running a quick smoke test before a full benchmark run.

How do I install Hugging Face Local Model Evals in Claude Code?

Run `npx skills add huggingface/skills --skill huggingface-community-evals -a claude-code`. Or copy the skill folder (skills/huggingface-community-evals in huggingface/skills) into .claude/skills/huggingface-community-evals in your project. Claude Code loads it when a task matches its description.

How do I install Hugging Face Local Model Evals in Codex?

Run `npx skills add huggingface/skills --skill huggingface-community-evals -a codex`. Or copy the skill folder (skills/huggingface-community-evals in huggingface/skills) into .agents/skills/huggingface-community-evals in your project. Codex loads it when a task matches its description.

Can I use Hugging Face Local Model Evals in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huggingface/skills --skill huggingface-community-evals -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/huggingface-community-evals, .gemini/skills/huggingface-community-evals, .github/skills/huggingface-community-evals and .opencode/skills/huggingface-community-evals in your project.

What does Hugging Face Local Model Evals need to run?

Going by SKILL.md and its folder, Hugging Face Local Model Evals needs Python for the scripts in its folder, the command-line tools its instructions call (uv) and credentials named HF_TOKEN. Our summary lists: uv for running the scripts; An HF_TOKEN for gated or private models; An NVIDIA GPU with nvidia-smi for local GPU runs.

Does Hugging Face Local Model Evals access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Hugging Face Local Model Evals safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Hugging Face Local Model Evals use?

Hugging Face Local Model Evals is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hugging Face Local Model Evals use?

About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hugging Face Local Model Evals?

Skills that share tags, products or a category with Hugging Face Local Model Evals: Hugging Face Community Evals (sickn33/agentic-awesome-skills, 47k stars), bitsandbytes Model Quantization (Orchestra-Research/AI-Research-SKILLs, 13k stars), Open Weights (ericrisco/rsc-harness, 174 stars) and LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hugging Face Local Model Evals?

huggingface (a GitHub organization, an official publisher) maintains it in huggingface/skills, which has 11,151 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 8, 2026.

Source: huggingface/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.