Update README.md

README.md

@@ -61,17 +61,12 @@ You can then use the completion mode of the GUI to experiment with this
 model. You can prompt the model for completions on the command line too:
 
 ```
-./Meta-Llama-3.1-405B.Q3_K_M.llamafile -p 'four score and seven' --log-disable
+./Meta-Llama-3.1-405B.Q2_K.llamafile -p 'four score and seven' --log-disable
 ```
 
 This model has a max context window size of 128k tokens. By default, a
-context window size of 4096 tokens is used. You can use a larger context
-window by passing the `-c 8192` flag. The software currently has
-limitations in its llama v3.1 support that may prevent scaling to the
-full 128k size. See our
-[Phi-3-medium-128k-instruct-llamafile](https://huggingface.co/Mozilla/Phi-3-medium-128k-instruct-llamafile)
-repository for llamafiles that are known to work with a 128kb context
-size.
+context window size of 8192 tokens is used. You can use the maximum
+context size by passing the `-c 0` flag.
 
 On Windows there's a 4GB limit on executable sizes. You can work around
 that by downloading the [official llamafile