Mention MLX
#3
by
pcuenq
HF Staff
- opened
README.md
CHANGED
|
@@ -20,6 +20,9 @@ Rene was pretrained on 1.5 trillion tokens of the [Dolma-1.7](https://huggingfac
|
|
| 20 |
For more details, see our [blog post](https://cartesia.ai/blog/on-device).
|
| 21 |
|
| 22 |
## Usage
|
|
|
|
|
|
|
|
|
|
| 23 |
### Installation
|
| 24 |
The Rene model depends on the `cartesia-pytorch` package, which can be installed with `pip` as follows:
|
| 25 |
```shell
|
|
|
|
| 20 |
For more details, see our [blog post](https://cartesia.ai/blog/on-device).
|
| 21 |
|
| 22 |
## Usage
|
| 23 |
+
|
| 24 |
+
This is the PyTorch version of the model, and it's intended to run on CUDA devices. For use on Mac computers, please use [the native MLX version](https://huggingface.co/cartesia-ai/Rene-v0.1-1.3b-4bit-mlx) instead.
|
| 25 |
+
|
| 26 |
### Installation
|
| 27 |
The Rene model depends on the `cartesia-pytorch` package, which can be installed with `pip` as follows:
|
| 28 |
```shell
|