mamba-1.4b-hf-f32 / README.md
Isaak Carter Augustus
e641b347704f958685c3acaf6613f1c9d40310c96c1867f5e7116f96ff7b62dd
0f88d4b verified
|
raw
history blame
594 Bytes
---
library_name: transformers
tags:
- mlx
base_model: state-spaces/mamba-1.4b-hf
---
# mlx-community/mamba-1.4b-hf-f32
The Model [mlx-community/mamba-1.4b-hf-f32](https://huggingface.co/mlx-community/mamba-1.4b-hf-f32) was converted to MLX format from [state-spaces/mamba-1.4b-hf](https://huggingface.co/state-spaces/mamba-1.4b-hf) using mlx-lm version **0.18.1**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/mamba-1.4b-hf-f32")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```