Configure a Hugging Face token

App version: 1.0.1iPad · iPhoneContent checked: 2026-09-21Screenshot UI: EnglishStandard / Pro

What you will do

Store a Hugging Face token and apply it to a newly started Python kernel.

Before you start

• An active Standard or Pro subscription, or an eligible trial.
• A working internet connection for the service or download used in this tutorial.
• A Hugging Face account and a token with the required resource permissions, if the resource requires authentication.

Download the tutorial workspace

Where to start

Settings → Environment → Hugging Face Token

Keep in mind

On iOS/iPadOS 1.0.1, completely close and reopen Vibeit after changing Environment settings. Restart Kernel clears the Python session but does not reload these saved settings.

Follow the steps

1. 1Open the Environment pageOpen Settings → Environment. The Hugging Face field is here, not in the AI provider list.
2. 2Enter your access tokenUse a token with access to the resources you need. Restricted models may also require approval of their access conditions on Hugging Face.
3. 3Close and reopen VibeitSave your work. Open the system app switcher, swipe Vibeit’s card upward to close it, then tap the Vibeit icon to open it again. Returning to the Home Screen alone does not restart the app.
4. 4Check presence and authorizationRun the example. HF_TOKEN present: True confirms the kernel has the token; Hugging Face authorization: OK confirms the service accepts it. Approval for a gated model remains a separate requirement.
   Copy code

   import os
   print("HF_TOKEN present:", bool(os.environ.get("HF_TOKEN")))
   try:
       from huggingface_hub import HfApi
       HfApi().whoami(token=True)
       print("Hugging Face authorization: OK")
   except Exception as error:
       status = getattr(getattr(error, "response", None), "status_code", None)
       print("Authorization error:", type(error).__name__, "HTTP:", status)
   

· Enlarge screenshot

1

See the control up close

PreviousNext

Close

1. Open the Environment page — Open Settings → Environment. The Hugging Face field is here, not in the AI provider list.

1

2. Enter your access token — Use a token with access to the resources you need. Restricted models may also require approval of their access conditions on Hugging Face.

2

3. Close and reopen Vibeit — Save your work. Open the system app switcher, swipe Vibeit’s card upward to close it, then tap the Vibeit icon to open it again. Returning to the Home Screen alone does not restart the app.

3

4. Check presence and authorization — Run the example. HF_TOKEN present: True confirms the kernel has the token; Hugging Face authorization: OK confirms the service accepts it. Approval for a gated model remains a separate requirement.

import os
print("HF_TOKEN present:", bool(os.environ.get("HF_TOKEN")))
try:
    from huggingface_hub import HfApi
    HfApi().whoami(token=True)
    print("Hugging Face authorization: OK")
except Exception as error:
    status = getattr(getattr(error, "response", None), "status_code", None)
    print("Authorization error:", type(error).__name__, "HTTP:", status)

4

Check the result

Run the example. HF_TOKEN present: True confirms the kernel has the token; Hugging Face authorization: OK confirms the service accepts it. Approval for a gated model remains a separate requirement.

If it does not work

• If a newly saved token or environment value is not visible to Python, restart the kernel.
• For 401/403 responses, check the token and the resource’s account permissions.
• If a file downloads but does not load, check its format, required packages and available memory.

Next steps

• Download and manage model files
• Set environment variables

Related reference

• Hugging Face access tokens
• Apple: quit and reopen an app

Contact support