Update README.md

README.md

@@ -27,7 +27,7 @@ Make sure your prompt ends with **SELECT** in order for the model to finish the
 ```python
 from mlx_lm import load, generate
 
-model, tokenizer = load("model="onekq-ai/OneSQL-v0.1-Qwen-7B-MLX-4bit")
+model, tokenizer = load(model="onekq-ai/OneSQL-v0.1-Qwen-7B-MLX-4bit")
 
 prompt="""CREATE TABLE students (
     id INTEGER PRIMARY KEY,
@@ -51,4 +51,4 @@ The model response is the finished SQL query without **SELECT**
 # User Experience
 
 Speed benchmark of this model is obtained on a MacBook Air with M1 processor and 8GB of RAM, the lower bound of Apple Silicon.
-On average, it took 16 seconds to generate a SQL query at 9 characters per second.
+On average, it took **16** seconds to generate a SQL query at **9** characters per second.