doc: update the usage code snippet

README.md

@@ -54,15 +54,51 @@ It can serve as a base model for further alignment, personalization, or integrat
 ## Get Started with the Model
 
 ```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Mehdi-Zogh/MNLP_M2_dpo_model"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# prepare the model input
+prompt = "explain gradient descent in simple terms."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=32768
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+# parsing thinking content
+try:
+    # rindex finding 151668 (</think>)
+    index = len(output_ids) - output_ids[::-1].index(151668)
+except ValueError:
+    index = 0
+
+thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
+content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
+
+print("thinking content:", thinking_content)
+print("content:", content)
 
-tokenizer = AutoTokenizer.from_pretrained("Mehdi-Zogh/MNLP_M2_dpo_model")
-model = AutoModelForCausalLM.from_pretrained("Mehdi-Zogh/MNLP_M2_dpo_model")
-
-prompt = "Explain how gradient descent works in simple terms."
-inputs = tokenizer(prompt, return_tensors="pt")
-outputs = model.generate(**inputs, max_new_tokens=200)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```