Inspect before downloading
See what is inside
These previews come from the published bundle files, so you can judge the method and writing before using it.
Tool guide
Hugging Face
Defines source-backed Hugging Face Hub and inference model selection, provenance, security, evaluation, and deployment review, evidence handling, and action boundaries.
Read the fileOverview
Hugging Face overview
Use this bundle to prepare source-backed Hugging Face Hub and inference model selection, provenance, security, evaluation, and deployment review and a review-ready Hugging Face model use.
Read the fileWorkflow
Hugging Face source-backed triage
1. State the requested decision or artifact. 2. Inventory evidence: Hugging Face surface, account, organization, repository, model, dataset, Space, provider, endpoint, and exact revision.
Read the fileTemplate
Hugging Face model use brief
Review-ready artifact for Hugging Face Hub and inference model selection, provenance, security, evaluation, and deployment review, evidence quality, verification, and controlled actions.
Read the fileIs this bundle right for your task?
Who it is for
- People who configure, operate, integrate, govern, or review work performed in Hugging Face
- Teams working in Technology, Business operations
When to use it
- A proposed Hugging Face configuration or workflow change needs current IDs, permissions, dependencies, tests, and rollback evidence.
- A report, export, integration, or automation result needs to be reconciled against actual workspace state and current product documentation.
What you need to provide
- The product version or workspace scope, relevant configuration or export, desired outcome, permissions, and accountable owner.
- Current IDs, settings, records, logs, screenshots, integration details, and test evidence needed to verify the requested change.
Tasks and expected outputs
Questions it helps answer
- Prepare a Hugging Face model use brief without fabricating local facts.
- Separate verified, provided, assumed, and missing evidence.
- Produce a review-ready decision with explicit verification and approval boundaries.
What it helps produce
- Hugging Face model use brief
Practical example
Use it with an agent
Load the bundle as context, provide the evidence named above, then adapt this example to your situation.
Provide the product version or workspace scope, relevant configuration or export, desired outcome, permissions, and accountable owner. Ask the agent to review Hugging Face and produce Hugging Face model use brief that maps configuration evidence, dependencies, permissions, tests, rollback, and actions that still require approval. Begin with huggingface.co — Inference Providers / En, then confirm that the reference is current and applicable. Inspect Hugging Face before drafting.
Context path: bundles/tools/hugging-face
What the bundle includes
Tools
- Hugging Face
Frameworks
- source-evidence matrix
- Hugging Face Hub and inference model selection, provenance, security, evaluation, and deployment review matrix
- qualified-review gate
Evaluations
- Hugging Face source verification check
Sources used to build this bundle
These are the public references behind the role definition and operating guidance. The bundle does not replace current documentation or evidence from your site.
Limitations and safe use
Do not use this for
- Changing live configuration, records, permissions, automations, integrations, or shared data without verified scope, testing, rollback, and approval.
Known limitations
- Use the listed authoritative sources for general role or tool behavior; local configuration, records, values, states, permissions, and results require inspected evidence.
- Task-specific work requires current evidence for Hugging Face surface, account, organization, repository, model, dataset, Space, provider, endpoint, and exact revision; model and dataset cards, license, files, provenance, gated access, token scope, remote-code and artifact scans; input data, privacy, provider routing and data policy, evaluation methods and results, hardware, latency, cost, monitoring, rollback, and approvals.
- Do not infer license compatibility, model safety, quality, provider selection, data handling, scan result, inference output, cost, or production readiness.
Safety notes
- Minimize personal, customer, employee, financial, credential, security, privileged, health, student, and other sensitive data.
- Require explicit confirmation before actions that download or execute untrusted model code, accept gated terms, send sensitive data, expose tokens, deploy endpoints or Spaces, publish artifacts, or incur inference charges.
- Route legal, privacy, security, compliance, financial, employment, clinical, safety, and other qualified judgments to an evidenced accountable reviewer.