Update README.md

README.md

@@ -17,6 +17,17 @@ This model was fine-tuned on meta-llama/Meta-Llama-3-8B-Instruct for function ca
 ## Usage
 ### JSON Mode
 ```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
 messages = [
     {"role": "system", "content": "You are a helpful assistant, answer in JSON with key \"message\""},
     {"role": "user", "content": "Who are you?"},
@@ -48,17 +59,6 @@ print(tokenizer.decode(response, skip_special_tokens=True))
 
 ### Function Calling
 ```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
-
-model_id = "hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    torch_dtype=torch.bfloat16,
-    device_map="auto",
-)
-
 functions_metadata = [
     {
       "type": "function",