Update README.md

Update default temperature from 0.6 to 0.7

Fix YAML syntax error in short_description

Update README with short description and project overview

Add custom chatbot component to chat interface

Update prompt reference text and space emoji

Align placeholder with default system prompt

Update default prompt text and appendix link

Update default prompt and fix chat interface inputs

update messages

Customize BeFM UI and defaults

Make code compatible with Gradio 6.0 structured content format

Fix Gradio ChatInterface: remove lambda wrapper, add lazy loading, make public

Switch to transformers version - vLLM uses too much memory on T4 GPU

Reduce vLLM GPU memory utilization to 0.7 to avoid OOM on T4 GPU

Switch to vLLM for faster inference with lazy loading and multi-turn fix

Fix multi-turn conversation: handle dict history format

Fix bugs: use token param, apply Llama 3.1 chat template, decode only new tokens

Add Be.FM-8B chat interface with PEFT adapter

initial commit