# Llamba Models

The Llamba models are part of Cartesia's [Edge](https://github.com/cartesia-ai/edge) library, designed for efficient, high-performance machine learning applications.

For more details, refer to the [paper](#).

---
## Usage

### Llamba on PyTorch

To use Llamba with PyTorch:

1. Install the required package:
 ```bash
 pip install --no-binary :all: cartesia-pytorch
 ```
2. Load and run the model
```python
from transformers import AutoTokenizer
from cartesia_pytorch.Llamba.llamba import LlambaLMHeadModel

model = LlambaLMHeadModel.from_pretrained("AvivBick/Llamba-1B", strict=True).to('cuda')
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B")
input_ids = tokenizer("Hello, my name is", return_tensors="pt").input_ids
input_ids = input_ids.to('cuda')
output = model.generate(input_ids, max_length=100)[0]
print(tokenizer.decode(output, skip_special_tokens=True))
```

### Llamba on MLX

To run Llamba with the Metal framework:  
_(Add specific instructions here when available.)_

---
### Evaluations

Details on model performance, benchmarks, and evaluation metrics can be found in the [paper link](#).  
_(Expand on this section if specific results or datasets are available.)_