Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,6 @@ The Llamba models are part of Cartesia's [Edge](https://github.com/cartesia-ai/e
|
|
| 5 |
For more details, refer to the [paper](#).
|
| 6 |
|
| 7 |
---
|
| 8 |
-
|
| 9 |
## Usage
|
| 10 |
|
| 11 |
### Llamba on PyTorch
|
|
@@ -29,14 +28,12 @@ output = model.generate(input_ids, max_length=100)[0]
|
|
| 29 |
print(tokenizer.decode(output, skip_special_tokens=True))
|
| 30 |
```
|
| 31 |
|
| 32 |
-
|
| 33 |
### Llamba on MLX
|
| 34 |
|
| 35 |
To run Llamba with the Metal framework:
|
| 36 |
_(Add specific instructions here when available.)_
|
| 37 |
|
| 38 |
---
|
| 39 |
-
|
| 40 |
### Evaluations
|
| 41 |
|
| 42 |
Details on model performance, benchmarks, and evaluation metrics can be found in the [paper link](#).
|
|
|
|
| 5 |
For more details, refer to the [paper](#).
|
| 6 |
|
| 7 |
---
|
|
|
|
| 8 |
## Usage
|
| 9 |
|
| 10 |
### Llamba on PyTorch
|
|
|
|
| 28 |
print(tokenizer.decode(output, skip_special_tokens=True))
|
| 29 |
```
|
| 30 |
|
|
|
|
| 31 |
### Llamba on MLX
|
| 32 |
|
| 33 |
To run Llamba with the Metal framework:
|
| 34 |
_(Add specific instructions here when available.)_
|
| 35 |
|
| 36 |
---
|
|
|
|
| 37 |
### Evaluations
|
| 38 |
|
| 39 |
Details on model performance, benchmarks, and evaluation metrics can be found in the [paper link](#).
|