Update README.md

README.md

@@ -39,13 +39,25 @@ To import this model with Python and run it, you can use the following code:
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_id = "azhiboedova/Meta-Llama-3.1-8B-Instruct-AQLM-2Bit-1x16"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
 
-# Example usage
-inputs = tokenizer("Hello, how can I assist you today?", return_tensors="pt")
-outputs = model.generate(inputs["input_ids"])
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
+)
+
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Translate English to German!: How are you?"},
+]
+
+outputs = pipeline(
+    messages,
+    max_new_tokens=256,
+)
+
+print(outputs[0]["generated_text"][-1]["content"])
 ```
 
 **Model Developers**