Update README.md
Browse files
README.md
CHANGED
@@ -9,7 +9,7 @@ datasets:
|
|
9 |
- dichspace/darulm
|
10 |
---
|
11 |
|
12 |
-
# mlx-community/Vikhr-7B-instruct_0.
|
13 |
This model was converted to MLX format from [`Vikhrmodels/Vikhr-7B-instruct_0.2`]() using mlx-lm version **0.6.0**.
|
14 |
Refer to the [original model card](https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_0.2) for more details on the model.
|
15 |
## Use with mlx
|
@@ -21,6 +21,6 @@ pip install mlx-lm
|
|
21 |
```python
|
22 |
from mlx_lm import load, generate
|
23 |
|
24 |
-
model, tokenizer = load("mlx-community/Vikhr-7B-instruct_0.
|
25 |
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
26 |
```
|
|
|
9 |
- dichspace/darulm
|
10 |
---
|
11 |
|
12 |
+
# mlx-community/Vikhr-7B-instruct_0.2-4bit
|
13 |
This model was converted to MLX format from [`Vikhrmodels/Vikhr-7B-instruct_0.2`]() using mlx-lm version **0.6.0**.
|
14 |
Refer to the [original model card](https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_0.2) for more details on the model.
|
15 |
## Use with mlx
|
|
|
21 |
```python
|
22 |
from mlx_lm import load, generate
|
23 |
|
24 |
+
model, tokenizer = load("mlx-community/Vikhr-7B-instruct_0.2_4 it")
|
25 |
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
26 |
```
|