Merge branch 'main' of https://github.com/igniterealtime/openfire-lla…

…ma-plugin

README.md

@@ -8,7 +8,7 @@ This plugin is a wrapper to llama.cpp server binary. It uses the HTTP API to cre
 
 ## Overview
 <img src="https://igniterealtime.github.io/openfire-llama-plugin/llama-chat.png" />
-https://igniterealtime.github.io/openfire-llama-plugin/llama-chat.webm
+https://igniterealtime.github.io/openfire-llama-plugin/llama-chat.mov
 
 ## Known Issues
 
@@ -92,4 +92,4 @@ The gguf model files for LLaMA 2 are large 5GB+ and may take serveral minutes to
 To speed up this process, you can preload the model by copying a local file to this destination and rename accordingly before installing the plugin.
 
 ### GPU Support
-The plugin has generic binaries for Linux64 and Windows64 with no GPU support. In order add GPU support, build the llama.cpp server binary with the appropriate GPU configuration and replace in the OPENFIRE_HOME/plugins/llama/classes/linux-64 or OPENFIRE_HOME/plugins/llama/classes/win-64 folder after installing the plugin or replace in the source code and rebuild plugin with maven.
+The plugin has generic binaries for Linux64 and Windows64 with no GPU support. In order add GPU support, build the llama.cpp server binary with the appropriate GPU configuration and replace in the OPENFIRE_HOME/plugins/llama/classes/linux-64 or OPENFIRE_HOME/plugins/llama/classes/win-64 folder after installing the plugin or replace in the source code and rebuild plugin with maven.