Update README.md

README.md

@@ -243,7 +243,7 @@ from llama_cpp import Llama
 
 # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
 llm = Llama(
-  model_path="./mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf",  # Download the model file first
+  model_path="./NT-Java-1.1B_Q4_K_M.gguf",  # Download the model file first
   n_ctx=2048,  # The max sequence length to use - note that longer sequence lengths require much more resources
   n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance
   n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available
@@ -251,7 +251,7 @@ llm = Llama(
 
 # Simple inference example
 output = llm(
-  "[INST] {prompt} [/INST]", # Prompt
+  "{prompt}", # Prompt
   max_tokens=512,  # Generate up to 512 tokens
   stop=["</s>"],   # Example stop token - not necessarily correct for this specific model! Please check before using.
   echo=True        # Whether to echo the prompt
@@ -259,7 +259,7 @@ output = llm(
 
 # Chat Completion API
 
-llm = Llama(model_path="./mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
+llm = Llama(model_path="./NT-Java-1.1B_Q4_K_M.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
 llm.create_chat_completion(
     messages = [
         {"role": "system", "content": "You are a story writing assistant."},