Changed license

Fixed compiling issue, added legnth penalty, and atttempting freezing encoder layers 0-5 to lower parameters and preserve T5's langauge understanding.

Clean up codebase and fix training bugs

Update LexiMind: improved training, model architecture, and evaluation

feat: Add FLAN-T5 compatibility with relative position bias

Build: Switch to Docker SDK for Hugging Face Spaces to support pyproject.toml

Docs: Add Hugging Face Spaces configuration to README

Refactor: Consolidate dependencies, improve testing, and add CI/CD

Fix app_file path to scripts/demo_gradio.py

Add LexiMind project files and models

chore: snapshot current refinements

Reformatted Project Structure

Initial commit