Olah is self-hosted lightweight huggingface mirror service. Olah
means hello
in Hilichurlian.
Other languages: 中文
- Models mirror
- Datasets mirror
- Spaces mirror
pip install olah
or:
pip install git+https://github.com/vtuber-plan/olah.git
- Clone this repository
git clone https://github.com/vtuber-plan/olah.git
cd olah
- Install the Package
pip install --upgrade pip
pip install -e .
Run the command in the console:
python -m olah.server
Then set the Environment Variable HF_ENDPOINT
to the mirror site (Here is http://localhost:8090).
export HF_ENDPOINT=http://localhost:8090
Starting from now on, all download operations in the HuggingFace library will be proxied through this mirror site.
from huggingface_hub import snapshot_download
snapshot_download(repo_id='Qwen/Qwen-7B', repo_type='model',
local_dir='./model_dir', resume_download=True,
max_workers=8)
You can check the path ./repos
which stores all cached datasets and models.
Run the command in the console:
python -m olah.server
Or you can specify the host address and listening port:
python -m olah.server --host localhost --port 8090
Please remember to change the --mirror-url
and --mirror-lfs-url
to the actual URLs of the mirror site while modifying the host and port.
The default mirror cache path is ./repos
, you can change it by --repos-path
parameter:
python -m olah.server --host localhost --port 8090 --repos-path ./hf_mirrors
- Authentication
- Administrator and user system
- OOS backend support
- Mirror Update Schedule Task
olah is released under the MIT License.