auto-serve local llama models

Update Hugging Face model

Add LOCAL_SERVING option to run against a local llama.cpp server

Log whether HF_TOKEN is present at startup (boolean only)

Use gemma instruct model that returns content directly

Fix chat styling, add clickable emotions, and dev ergonomics

Disable Gradio SSR mode to fix HF Space port conflict

Add Inside Out emotion chat app built with Gradio

Duplicate from gradio-templates/chatbot