Changed the chatbot model from SMILE llama 8B to Mental llama 7B

Added debugging statements

Updated the message format due to Gradio format

Updated the chat function into going through each chat item in history

Added requests

Switched back to HF InferenceClient

Switched to a model specific generation endpoint

Switched to HF Router API

Removed InferenceClient.text_generation() and used direct inference API endpoint fallback.

Defined provider in and use Inference with model_id

refactor: migrate chatbot inference from local PEFT model to Hugging Face hosted text-generation API

Added chatbot import generate_response

Added gradio import

Created requirements file

Add hosted chatbot backend using Hugging Face Inference API

Update the app.py

initial commit

Duplicate from gradio-templates/chatbot