Upload folder using huggingface_hub
Browse files
README.md
CHANGED
@@ -14,10 +14,16 @@ inference:
|
|
14 |
# pcuenq/My-Mistral-7B-v0.1-4bit
|
15 |
This model was converted to MLX format from [`mistralai/Mistral-7B-v0.1`]().
|
16 |
Refer to the [original model card](https://huggingface.co/mistralai/Mistral-7B-v0.1) for more details on the model.
|
|
|
17 |
## Use with mlx
|
|
|
18 |
```bash
|
19 |
-
pip install mlx
|
20 |
-
|
21 |
-
|
22 |
-
python
|
|
|
|
|
|
|
|
|
23 |
```
|
|
|
14 |
# pcuenq/My-Mistral-7B-v0.1-4bit
|
15 |
This model was converted to MLX format from [`mistralai/Mistral-7B-v0.1`]().
|
16 |
Refer to the [original model card](https://huggingface.co/mistralai/Mistral-7B-v0.1) for more details on the model.
|
17 |
+
|
18 |
## Use with mlx
|
19 |
+
|
20 |
```bash
|
21 |
+
pip install mlx-lm
|
22 |
+
```
|
23 |
+
|
24 |
+
```python
|
25 |
+
from mlx_lm import load, generate
|
26 |
+
|
27 |
+
model, tokenizer = load("pcuenq/My-Mistral-7B-v0.1-4bit")
|
28 |
+
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
29 |
```
|