Update README.md

README.md

@@ -47,7 +47,8 @@ model, tokenizer = FastLanguageModel.from_pretrained(
 
 FastLanguageModel.for_inference(model)  # Enable native 2x faster inference
 
-messages = [{"role": "user", "content": "<guidance_prompt>Count the number of 'r's in the word 'strawberry,' and then write a Python script that checks if an arbitrary word contains the same number of 'r's.</guidance_prompt>"}]
+guidance_prompt = """<guidance_prompt>Count the number of 'r's in the word 'strawberry,' and then write a Python script that checks if an arbitrary word contains the same number of 'r's.</guidance_prompt>"""
+messages = [{"role": "user", "content": guidance_prompt}]
 inputs = tokenizer.apply_chat_template(
     messages,
     tokenize=True,
@@ -58,5 +59,8 @@ inputs = tokenizer.apply_chat_template(
 outputs = model.generate(input_ids=inputs, max_new_tokens=2000, use_cache=True, early_stopping=True, temperature=0)
 result = tokenizer.batch_decode(outputs)
 
-print(result[0][len(input_data):].replace("</s>", ""))
-```
+print(result[0][len(guidance_prompt):].replace("</s>", ""))
+```
+
+# Disclaimer
+The model may occasionally fail to generate complete guidance, especially when the prompt includes specific instructions on how the responses should be structured. This limitation arises from the way the model was trained.