Update README.md

README.md

@@ -1,19 +1,17 @@
-This model was exported using [GPTQModel](https://github.com/ModelCloud/GPTQModel). Below is example code for exporting a model from GPTQ format to MLX format.
+This model was exported using [GPTQModel](https://github.com/ModelCloud/GPTQModel). 
 
-## Example:
-```python
-from gptqmodel import GPTQModel
+## How to run this model
 
-# load gptq quantized model
-gptq_model_path = "ModelCloud/Qwen2.5-Coder-32B-Instruct-gptqmodel-4bit-vortex-v1"
-mlx_path = f"./vortex/ModelCloud/Qwen2.5-Coder-32B-Instruct-gptqmodel-4bit-vortex-mlx-v1"
+```shell
+# install mlx
+pip install mlx_lm
+```
 
-# export to mlx model
-GPTQModel.export(gptq_model_path, mlx_path, "mlx")
 
-# load mlx model check if it works
+```python
 from mlx_lm import load, generate
 
+mlx_path = "ModelCloud/Qwen2.5-Coder-32B-Instruct-gptqmodel-4bit-vortex-mlx-v1"
 mlx_model, tokenizer = load(mlx_path)
 prompt = "The capital of France is"
 
@@ -23,4 +21,21 @@ prompt = tokenizer.apply_chat_template(
 )
 
 text = generate(mlx_model, tokenizer, prompt=prompt, verbose=True)
+```
+
+### Export gptq to mlx
+```shell
+# install gptqmodel with mlx
+pip install gptqmodel[mlx] --no-build-isolation
+```
+
+```python
+from gptqmodel import GPTQModel
+
+# load gptq quantized model
+gptq_model_path = "ModelCloud/Qwen2.5-Coder-32B-Instruct-gptqmodel-4bit-vortex-v1"
+mlx_path = f"./vortex/ModelCloud/Qwen2.5-Coder-32B-Instruct-gptqmodel-4bit-vortex-mlx-v1"
+
+# export to mlx model
+GPTQModel.export(gptq_model_path, mlx_path, "mlx")
 ```