Improve docs

docs/mlx_deploy_guide.md

@@ -12,7 +12,7 @@ Run, serve, and fine-tune [**MiniMax-M2**](https://huggingface.co/MiniMaxAI/Mini
 Install the `mlx-lm` package via pip:
 
 ```bash
-pip install mlx-lm
+pip install -U mlx-lm
 ```
 
 **CLI**
@@ -62,7 +62,7 @@ print(response)
 ```
 
 **Tips**
-- **Model variants**: Check [Hugging Face](https://huggingface.co/collections/mlx-community/minimax-m2) for `MiniMax-M2-4bit`, `6bit`, `8bit`, or `bfloat16` versions.
+- **Model variants**: Check this [MLX community collection on Hugging Face](https://huggingface.co/collections/mlx-community/minimax-m2) for `MiniMax-M2-4bit`, `6bit`, `8bit`, or `bfloat16` versions.
 - **Fine-tuning**: Use `mlx-lm.lora` for efficient parameter-efficient fine-tuning (PEFT).
 
 **Resources**