Nice extension, but can you fix it to follow different prompt formats. For example, it doesn't respect or use <|end_of_text|> tokens for ChatML models and keeps outputting more and more text.
I rarely leave reviews for things, but this is an extension that deserves to be better known. When you're just getting into local LLMs, it's exactly this sort of simple local Web UI that's needed. No need for hours tinkering with CLI and GUI interfaces. Straight into the action with this.
