> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gpuhub.com/llms.txt
> Use this file to discover all available pages before exploring further.

# HuggingFace

> The platform where the machine learning community collaborates on models, datasets, and applications.

<img src="https://mintcdn.com/gpuhub/r1V0ko0l9sh4RwWM/images/logo-huggingface.png?fit=max&auto=format&n=r1V0ko0l9sh4RwWM&q=85&s=495f5e5b7fbaf9c561ab1e1f414d5b7c" alt="" width="64" height="64" data-path="images/logo-huggingface.png" />

## Common Issues

The models downloaded from HuggingFace take up a lot of system disk space, causing the system disk space to run out.

By default, HuggingFace caches models in the /root/.cache directory. You can save the model cache to the data disk by following these methods:

Execute in the terminal:

```bash bash theme={null}
export HF_HOME=/root/gpuhub-tmp/cache/
```

Or execute in Python code:

```Python python theme={null}
import os
os.environ['HF_HOME'] = '/root/gpuhub-tmp/cache/'
```