Update README.md

README.md

@@ -61,10 +61,9 @@ model. You can prompt the model for completions on the command line too:
 ```
 
 This model has a max context window size of 128k tokens. By default, a
-context window size of 512 tokens is used. You may increase this to the
-maximum by passing the `-c 0` flag, which uses considerable memory. A
-context window of `-c 32768` ought to be big enough for most use cases
-and it incurs significantly less memory overhead.
+context window size of 512 tokens is used. You can use a larger context
+window by passing the `-c 8192` flag. The software currently has
+limitations that may prevent scaling to the full 128k size.
 
 On GPUs with sufficient RAM, the `-ngl 999` flag may be passed to use
 the system's NVIDIA or AMD GPU(s). On Windows, only the graphics card