Add mentions of MLX-my-repo.

This commit is contained in:
Vaibhav Srivastav 2024-11-29 14:51:23 +01:00
parent cefe793ae0
commit 7c59bfeff2
2 changed files with 3 additions and 1 deletions

View File

@ -77,7 +77,7 @@ to see how to use the API in more detail.
The `mlx-lm` package also comes with functionality to quantize and optionally The `mlx-lm` package also comes with functionality to quantize and optionally
upload models to the Hugging Face Hub. upload models to the Hugging Face Hub.
You can convert models in the Python API with: You can convert models directly via the Hugging Face Space [here](https://huggingface.co/spaces/mlx-community/mlx-my-repo) or in the Python API with:
```python ```python
from mlx_lm import convert from mlx_lm import convert

View File

@ -8,3 +8,5 @@ parent directory.
This package also supports fine tuning with LoRA or QLoRA. For more information This package also supports fine tuning with LoRA or QLoRA. For more information
see the [LoRA documentation](LORA.md). see the [LoRA documentation](LORA.md).
🆕 You can directly convert models in Q4/ Q8 via the Hugging Face Space [here](https://huggingface.co/spaces/mlx-community/mlx-my-repo).