Instructions to use akkikiki/j-moshi-ext-mlx-q8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use akkikiki/j-moshi-ext-mlx-q8 with Moshi:
# pip install moshi_mlx # Run local inference (macOS Apple Silicon) python -m moshi_mlx.local -q 8 --hf-repo "akkikiki/j-moshi-ext-mlx-q8" # Or run with web UI python -m moshi_mlx.local_web -q 8 --hf-repo "akkikiki/j-moshi-ext-mlx-q8"
- Notebooks
- Google Colab
- Kaggle
|
Download README.md from akkikiki/j-moshi-ext-mlx-q8: direct link, hf CLI and curl.
- Browser
- Download file 890 Bytes
-
https://huggingface.co/akkikiki/j-moshi-ext-mlx-q8/resolve/56aeec24da642703e90eac5cc52f7af3ea56ba4d/README.md
- Command line
-
hf download hf://akkikiki/j-moshi-ext-mlx-q8@56aeec24da642703e90eac5cc52f7af3ea56ba4d/README.md
-
curl -L -o README.md https://huggingface.co/akkikiki/j-moshi-ext-mlx-q8/resolve/56aeec24da642703e90eac5cc52f7af3ea56ba4d/README.md
890 Bytes
metadata
license: cc-by-nc-4.0
language:
- ja
base_model:
- akkikiki/j-moshi-ext-mlx
base_model_relation: quantized
library_name: moshi
tags:
- 8-bit precision
The model in this repository is an MLX model converted from the pre-trained J-Moshi model for Mac OS.
For other terms and restrictions, it adheres to the original models nu-dialogue/j-moshi-ext and kyutai/moshi.
このリポジトリのモデルは,J-Moshiの学習済みモデルをMac OS向けに変換したMLXモデルです。
その他規約・制限等においてはオリジナルのモデルであるnu-dialogue/j-moshi-ext並びにkyutai/moshiに準拠します。
Installation
pip install moshi_mlx
詳細はhttps://github.com/kyutai-labs/moshi?tab=readme-ov-file#requirements を参照。
Example Usage
python -m moshi_mlx.local --hf-repo akkikiki/j-moshi-ext-mlx-q8 --quantized 8