Update README.md

README.md

@@ -142,7 +142,7 @@ 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="./capybarahermes-2.5-mistral-7b.Q4_K_M.gguf",  # Download the model file first
+  model_path="./mixtral-8x22b-v0.1-instruct-oh-Q8_0-00001-of-00004.gguf",  # Download the model file first
   n_ctx=32768,  # 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
@@ -158,7 +158,7 @@ output = llm(
 
 # Chat Completion API
 
-llm = Llama(model_path="./capybarahermes-2.5-mistral-7b.Q4_K_M.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
+llm = Llama(model_path="./mixtral-8x22b-v0.1-instruct-oh-Q8_0-00001-of-00004.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."},