Increase max_new_tokens in generate method to 1000 for enhanced output capacity

Update ME_LLAMA_MODEL to use the Llama-3.1-8B-Instruct variant and improve fallback model logging

Update ME_LLAMA_MODEL to use the 13b variant for improved performance

Update model configurations to use new model paths and adjust tensor data types; increase max_new_tokens and modify sampling parameters in generate method for improved output quality.

model update

model and ui update

Update max_new_tokens in generate method and enhance consultation prompt for clarity

Update conversation turn limit and enhance prompts for medical consultation app

Implement medical consultation app with LangChain memory management and model integration