Update README.md

README.md

@@ -64,6 +64,7 @@ model = AutoModelForCausalLM.from_pretrained(
 model.generation_config.pad_token_id = tokenizer.eos_token_id
 
 # Inference simple as transformers library
+prompt = "Describe basics of DNNs quantization."
 messages = [
                 {
                     "role": "system",
@@ -71,7 +72,7 @@ messages = [
                 },
                 {
                     "role": "user",
-                    "content": "Describe basics of DNNs quantization."
+                    "content": prompt
                 }
             ]