Update README.md
Browse files
README.md
CHANGED
|
@@ -20,10 +20,9 @@ This version significantly reduces inference memory requirements (~90 GB RAM),
|
|
| 20 |
|
| 21 |
The model was created using the following steps:
|
| 22 |
|
| 23 |
-
pip uninstall mlx-lm
|
| 24 |
-
pip install git+https://github.com/ml-explore/mlx-lm.git@main
|
| 25 |
-
|
| 26 |
-
mlx_lm.convert \
|
| 27 |
--hf-path openai/gpt-oss-120b \
|
| 28 |
--quantize \
|
| 29 |
--q-bits 6 \
|
|
|
|
| 20 |
|
| 21 |
The model was created using the following steps:
|
| 22 |
|
| 23 |
+
* pip uninstall mlx-lm
|
| 24 |
+
* pip install git+https://github.com/ml-explore/mlx-lm.git@main
|
| 25 |
+
* mlx_lm.convert \
|
|
|
|
| 26 |
--hf-path openai/gpt-oss-120b \
|
| 27 |
--quantize \
|
| 28 |
--q-bits 6 \
|