Update README.md

README.md

@@ -47,9 +47,9 @@ Running the following on a desktop OS will launch a tab in your web
 browser with a chatbot interface.
 
 ```
-wget https://huggingface.co/Mozilla/Meta-Llama-3.1-70B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-70B-Instruct.Q6_K.llamafile
-chmod +x Meta-Llama-3.1-70B-Instruct.Q6_K.llamafile
-./Meta-Llama-3.1-70B-Instruct.Q6_K.llamafile
+wget https://huggingface.co/Mozilla/Meta-Llama-3.1-70B-Instruct-llamafile/resolve/main/Meta-Llama-3.1-70B-Instruct.Q5_0.llamafile
+chmod +x Meta-Llama-3.1-70B-Instruct.Q5_0.llamafile
+./Meta-Llama-3.1-70B-Instruct.Q5_0.llamafile
 ```
 
 You then need to fill out the prompt / history template (see below).
@@ -71,6 +71,14 @@ Having **trouble?** See the ["Gotchas"
 section](https://github.com/mozilla-ocho/llamafile/?tab=readme-ov-file#gotchas)
 of the README.
 
+## About Upload Limits
+
+Hugging Face has a 50GB upload limit. Some of the llamafiles in this
+repository are so large that they need to be uploaded in multiple files.
+Those files will have `.cat𝑋.llamafile` at the end of the filename. If
+you want to download one of these larger models, then you'll need to to
+use the `cat` command to concatenate them back into a single file.
+
 ## Prompting
 
 To have a good working chat experience when using the web GUI, you need