Update README.md

README.md

@@ -157,14 +157,51 @@ You can easily integrate Nous-V1 4B via the Hugging Face Transformers library or
 ### Using Hugging Face Transformers
 
 ```python
-# Use a pipeline as a high-level helper
-from transformers import pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-pipe = pipeline("text-generation", model="apexion-ai/Nous-V1-4B")
+model_name = "apexion-ai/Nous-1-4B"
+
+# 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 = "Give me a short introduction to large language model."
 messages = [
-    {"role": "user", "content": "Who are you?"},
+    {"role": "user", "content": prompt}
 ]
-pipe(messages)
+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)
+
 ```
 
 ### Deployment Options