Instructions to use akkikiki/j-moshi-ext-mlx-q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use akkikiki/j-moshi-ext-mlx-q4 with Moshi:
# pip install moshi_mlx # Run local inference (macOS Apple Silicon) python -m moshi_mlx.local -q 4 --hf-repo "akkikiki/j-moshi-ext-mlx-q4" # Or run with web UI python -m moshi_mlx.local_web -q 4 --hf-repo "akkikiki/j-moshi-ext-mlx-q4"
- Notebooks
- Google Colab
- Kaggle
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-q4 --quantized 4
- Downloads last month
- 14
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for akkikiki/j-moshi-ext-mlx-q4
Base model
kyutai/moshiko-pytorch-bf16 Finetuned
nu-dialogue/j-moshi-ext Finetuned
akkikiki/j-moshi-ext-mlx