|
--- |
|
language: |
|
- ru |
|
- en |
|
tags: |
|
- mlx |
|
datasets: |
|
- zjkarina/Vikhr_instruct |
|
- dichspace/darulm |
|
--- |
|
|
|
# mlx-community/Vikhr-7B-instruct_0.2-4bit |
|
This model was converted to MLX format from [`Vikhrmodels/Vikhr-7B-instruct_0.2`]() using mlx-lm version **0.6.0**. |
|
Refer to the [original model card](https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_0.2) 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/Vikhr-7B-instruct_0.2-4bit") |
|
response = generate(model, tokenizer, prompt="Привет", verbose=True) |
|
``` |
|
|
