Update README.md
Browse files
README.md
CHANGED
@@ -24,13 +24,19 @@ widget:
|
|
24 |
'
|
25 |
---
|
26 |
|
27 |
-
# TinyLlama-1.1B-Chat-v1.0-mlx
|
28 |
This model was converted to MLX format from [`TinyLlama/TinyLlama-1.1B-Chat-v1.0`]().
|
29 |
Refer to the [original model card](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) for more details on the model.
|
30 |
## Use with mlx
|
|
|
31 |
```bash
|
32 |
-
pip install mlx
|
33 |
-
git clone https://github.com/ml-explore/mlx-examples.git
|
34 |
-
cd mlx-examples/llms/hf_llm
|
35 |
-
python generate.py --model mlx-community/TinyLlama-1.1B-Chat-v1.0-mlx --prompt "My name is"
|
36 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
'
|
25 |
---
|
26 |
|
27 |
+
# mlx-community/TinyLlama-1.1B-Chat-v1.0-mlx
|
28 |
This model was converted to MLX format from [`TinyLlama/TinyLlama-1.1B-Chat-v1.0`]().
|
29 |
Refer to the [original model card](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) for more details on the model.
|
30 |
## Use with mlx
|
31 |
+
|
32 |
```bash
|
33 |
+
pip install mlx-lm
|
|
|
|
|
|
|
34 |
```
|
35 |
+
|
36 |
+
```python
|
37 |
+
from mlx_lm import load, generate
|
38 |
+
|
39 |
+
model, tokenizer = load("mlx-community/TinyLlama-1.1B-Chat-v1.0-mlx")
|
40 |
+
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
41 |
+
```
|
42 |
+
|