Update README.md

README.md

@@ -44,12 +44,34 @@ $ pip install transformers==4.51.3
 Then, copy the snippet from the section that is relevant for your use case.
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-tokenizer = AutoTokenizer.from_pretrained("inclusionAI/GroveMoE-Inst", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("inclusionAI/GroveMoE-Inst", device_map="auto", trust_remote_code=True).eval()
-inputs = tokenizer('### Human:\nHow are you?\n### Assistant:\n', return_tensors='pt')
-inputs = inputs.to(model.device)
-pred = model.generate(**inputs)
-print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
+model_name = "inclusionAI/GroveMoE-Inst"
+# 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": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=16384
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+content = tokenizer.decode(output_ids, skip_special_tokens=True)
+
+print("content:", content)
 ```
 
 ## Citation