monster/Qwen-Image-Layered-MRP-MLX
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

more details for usage

Browse Source
This commit is contained in:
Anthony Wu 2024-11-09 08:19:02 -08:00
parent 48d2e71207
commit 08b390dc7b
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -57,10 +57,18 @@ to get the `mflux-generate` and related command line executables. You can skip t
<details>
<summary>For Python 3.13 dev preview</summary>
The [T5 encoder](https://huggingface.co/docs/transformers/en/model_doc/t5) is dependent on [sentencepiece](https://pypi.org/project/sentencepiece/), which does not have a installable wheel artifact for Python 3.13 as of Nov 2024. Until Google [publishes a 3.13 wheel](https://pypi.org/project/sentencepiece/), you need to build your own wheel with [official build instructions](https://github.com/google/sentencepiece/blob/master/python/README.md#build-and-install-sentencepiece) or for your convenience use a `.whl` pre-built by contributor @anthonywu. The steps below should work for most developers though your system may vary.
```sh
uv venv --python 3.13
python -V # e.g. Python 3.13.0rc2
source .venv/bin/activate
# for your convenience, you can use the contributor wheel
uv pip install https://github.com/anthonywu/sentencepiece/releases/download/0.2.1-py13dev/sentencepiece-0.2.1-cp313-cp313-macosx_11_0_arm64.whl
# enable the pytorch nightly
uv pip install --pre --extra-index-url https://download.pytorch.org/whl/nightly -e .
```
</details>