Update README.md

README.md

@@ -16,7 +16,7 @@ tags:
 
 
 ```
-./main -t 10 -ngl 32 -m persian_llama_7b.f32.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: یک شعر حماسی در مورد کوه دماوند بگو ### Input:  ### Response:"
+./main -t 10 -ngl 32 -m persian_llama_7b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: یک شعر حماسی در مورد کوه دماوند بگو ### Input:  ### Response:"
 ```
 Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.
 
@@ -53,7 +53,7 @@ callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
 
 # Make sure the model path is correct for your system!
 llm = LlamaCpp(
-    model_path="./persian_llama_7b.f32.gguf",
+    model_path="./persian_llama_7b.Q4_K_M.gguf",
     n_gpu_layers=n_gpu_layers, n_batch=n_batch,
     callback_manager=callback_manager,
     verbose=True,