Skip to main content
TabPFN-2.5 is released under a non-commerical license, which you need to accept before the model files can be downloaded.

​
Step 1: Accept the license agreement

Visit Hugging Face, where the model is hosted, and agree to the license terms: https://huggingface.co/Prior-Labs/tabpfn_2_5/ You will need to log in to your Hugging Face account, or create one if you don’t already have it. Once you have agreed to the license, you should be granted access immediately.

​
Step 2: Create an access token

  • If you created a new account: ensure you have verified your Hugging Face email address
  • Create a new token using this link: https://huggingface.co/settings/tokens/new?tokenType=fineGrained
    • Give the token a name
    • Check the box “Read access to contents of all public gated repos you can access” ( screenshot)
  • Press “Create token”, and copy the displayed token (you will only be able to see it once).
    Your token should look like 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

​
Step 3: Log in with your new token

​
If using Google Colab

  • Select “Secrets” from the left-hand menu (screenshot)
  • Create a new secret. Set name to “HF_TOKEN” and value to the token itself
  • Ensure that “Notebook access” is enabled

​
If using a notebook other than Google Colab

Ensure TabPFN is installed. Create a new Python code cell containing: 
import huggingface_hub
huggingface_hub.login()
Execute this cell and follow the instructions.

​
If using the terminal

  • Activate the Python environment that you use for TabPFN
  • Run hf auth login
  • Enter the token when prompted

​
In scripts or CI pipelines

Configure your environment to specify the HF_TOKEN environment variable. For more information, refer to the Hugging Face documentation.