|
--- |
|
language: |
|
- fr |
|
- it |
|
- de |
|
- es |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- moe |
|
- mlx |
|
--- |
|
|
|
# mlx-community/mixtral-8x22b-4bit |
|
This model was converted to MLX format from [`v2ray/Mixtral-8x22B-v0.1`](https://huggingface.co/v2ray/Mixtral-8x22B-v0.1) using mlx-lm version **0.4.0**. |
|
|
|
Model added by [Prince Canuma](https://twitter.com/Prince_Canuma). |
|
|
|
Refer to the [original model card](https://huggingface.co/v2ray/Mixtral-8x22B-v0.1) for more details on the model. |
|
|
|
## Use with mlx |
|
|
|
```bash |
|
pip install mlx-lm |
|
``` |
|
|
|
```python |
|
from mlx_lm import load, generate |
|
|
|
model, tokenizer = load("mlx-community/mixtral-8x22b-4bit") |
|
response = generate(model, tokenizer, prompt="hello", verbose=True) |
|
``` |
|
|
