Update README.md

README.md

@@ -36,7 +36,7 @@ The Model file is based on ggml-model-Q2_K.gguf.
 
 A single GPU with 24GB of memory can hold 4 layers of data, and num_gpu is set to 4, num_ctx is set to 2048.
 
-If there are 8 GPUs with 24GB of GPU memory each, num_gpu can be 32.
+If there are 8 GPUs with 24GB of GPU memory each, num_gpu can be 32. The value of this parameter can be set to ollama.
 
 The specific parameters can be changed according to your own tests.
 
@@ -84,9 +84,12 @@ ollama run huihui_ai/perplexity-ai-r1:671b-q2_K
 ```
 /set parameter num_ctx 2048
 ```
+```
+/set parameter num_gpu 32
+```
 ![image/png](png/02.png)
 
-The two parameters above should be set one at a time, and there's no need to send both to ollama at the same time.
+The three parameters above should be set one at a time, and there's no need to send both to ollama at the same time.
 
 
 6. **We will upload q2_K shortly.**