Updated Readme

README.md

@@ -76,7 +76,7 @@ model_llama = AutoAWQForCausalLM.from_quantized(model_id_llama, fuse_layer=True,
 
 # Set up the prompt and prompt template. Change instruction as per requirements.
 prompt_llama = "Tell me a funny joke about Large Language Models meeting a Blackhole in an intergalactic Bar."
-fromatted_prompt = f'''[INST] <<SYS>> You are a helpful, and fun loving assistant. Always answer as jestfully as possible. <</SYS>> {prompt_llama} [/INST] '''
+fromatted_prompt = f'''<s> [INST] You are a helpful, and fun loving assistant. Always answer as jestfully as possible.[/INST] </s> [INST] {prompt_llama}[/INST]'''
 
 tokens = tokenizer_llama(fromatted_prompt, return_tensors="pt").input_ids.cuda()