Update README.md

README.md

@@ -45,7 +45,7 @@ We advise you to clone [`llama.cpp`](https://github.com/ggerganov/llama.cpp) and
 huggingface-cli download xverse/XVERSE-7B-Chat-GGUF xverse-7b-chat-q4_k_m.gguf --local-dir . --local-dir-use-symlinks False
 ```
 
-我们演示了如何使用 `llama.cpp` 来运行xverse-7b gguf模型:
+我们演示了如何使用 `llama.cpp` 来运行xverse-7b-chat-q4_k_m.gguf模型:
 
 ```bash
 ./main -m xverse-7b-chat-q4_k_m.gguf -n 512 --color -i --temp 0.85 --top_k 30 --top_p 0.85 --repeat_penalty 1.1 -ins  # -ngl 99 for GPU
@@ -59,7 +59,7 @@ Cloning the repo may be inefficient, and thus you can manually download the GGUF
 huggingface-cli download xverse/XVERSE-7B-Chat-GGUF xverse-7b-chat-q4_k_m.gguf --local-dir . --local-dir-use-symlinks False
 ```
 
-We demonstrate how to use `llama.cpp` to run xverse-7b gguf model:
+We demonstrate how to use `llama.cpp` to run xverse-7b-chat-q4_k_m.gguf model:
 
 ```shell
 ./main -m xverse-7b-chat-q4_k_m.gguf -n 512 --color -i --temp 0.85 --top_k 30 --top_p 0.85 --repeat_penalty 1.1 -ins  # -ngl 99 for GPU