Qubitium commited on
Commit
689c12f
·
verified ·
1 Parent(s): e838d0e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -7
README.md CHANGED
@@ -1,14 +1,12 @@
1
  This model was exported using [GPTQModel](https://github.com/ModelCloud/GPTQModel).
2
 
3
- ## How To Use
4
-
5
- ### Use the model
6
 
7
  ```shell
 
8
  pip install mlx_lm
9
  ```
10
 
11
- Install mlx_lm first
12
 
13
  ```python
14
  from mlx_lm import load, generate
@@ -27,11 +25,10 @@ text = generate(mlx_model, tokenizer, prompt=prompt, verbose=True)
27
 
28
  ### Export gptq to mlx
29
  ```shell
30
- pip install gptqmodel
 
31
  ```
32
 
33
- Install gptqmodel first
34
-
35
  ```python
36
  from gptqmodel import GPTQModel
37
 
 
1
  This model was exported using [GPTQModel](https://github.com/ModelCloud/GPTQModel).
2
 
3
+ ## How to run this model
 
 
4
 
5
  ```shell
6
+ # install mlx
7
  pip install mlx_lm
8
  ```
9
 
 
10
 
11
  ```python
12
  from mlx_lm import load, generate
 
25
 
26
  ### Export gptq to mlx
27
  ```shell
28
+ # install gptqmodel with mlx
29
+ pip install gptqmodel[mlx] --no-build-isolation
30
  ```
31
 
 
 
32
  ```python
33
  from gptqmodel import GPTQModel
34