update README

README.md

@@ -46,7 +46,7 @@ We advise you to clone [`llama.cpp`](https://github.com/ggerganov/llama.cpp) and
 In the following demonstration, we assume that you are running commands under the repository `llama.cpp`.
 
 ```shell
-./llama-cli -hf Qwen/Qwen3-1.7B:Q8_0 --jinja --color -ngl 99 -fa -sm row --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0 --presence-penalty 1.5 -c 40960 -n 32768 --no-context-shift
+./llama-cli -hf Qwen/Qwen3-1.7B-GGUF:Q8_0 --jinja --color -ngl 99 -fa -sm row --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0 --presence-penalty 1.5 -c 40960 -n 32768 --no-context-shift
 ```
 
 ### ollama

params

@@ -9,5 +9,6 @@
     "presence_penalty" : 1.5,
     "top_k" : 20,
     "top_p" : 0.95,
-    "num_predict" : 32768
+    "num_predict" : 32768,
+    "num_ctx": 40960
 }