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
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,7 @@ language:
|
|
| 5 |
base_model:
|
| 6 |
- akkikiki/j-moshi-ext-mlx
|
| 7 |
base_model_relation: quantized
|
| 8 |
-
library_name:
|
| 9 |
tags:
|
| 10 |
- 8-bit precision
|
| 11 |
---
|
|
|
|
| 5 |
base_model:
|
| 6 |
- akkikiki/j-moshi-ext-mlx
|
| 7 |
base_model_relation: quantized
|
| 8 |
+
library_name: moshi
|
| 9 |
tags:
|
| 10 |
- 8-bit precision
|
| 11 |
---
|