Update README.md

README.md

@@ -51,24 +51,28 @@ To utilize the LlamaLens model for inference, follow these steps:
 Use the transformers library to load the LlamaLens model and its tokenizer:
 
 ```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import pipeline
 
 model_name = "QCRI/LlamaLens"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+pipe = pipeline("text-generation", model=model_name)
 ```
 3. **Prepare the Input:**:
 Tokenize your input text:
 ```python
 input_text = "Your input text here"
-inputs = tokenizer(input_text, return_tensors="pt")
+system_message = "Your system message text here"
+messages = [
+    {"role": "system", "content": system_message},
+    {"role": "user", "content": input_text},
+]
+
+
 ```
 4. **Generate the Output:**:
 Generate a response using the model:
 ```python
-output = model.generate(**inputs)
-response = tokenizer.decode(output[0], skip_special_tokens=True)
-print(response)
+generated_text = pipe(messages, num_return_sequences=1)
+print(generated_text)
 ```
 
 ## Results