fix

fix: add session state for concurrency and resolve stopping criteria bugs

reduce tokens

feat: add stop button and loading states

feat: add token limit warning and truncation notice for CPU transparency

Update requirements.txt

feat: token streaming with TextIteratorStreamer for real-time output

fix: remove @spaces.GPU decorator - not compatible with CPU basic

feat: streaming output - show base model result while fine-tuned generates

feat: migrate to ZeroGPU for free GPU inference

reduce max_new_tokens to test

fix: Gradio 6.0 compatibility - move theme to launch, remove show_copy_button

Add requirements.txt

Update application file

Add application file

initial commit