- Changed from Apache 2.0 only to dual license model
- Apache 2.0 for research, education, and non-commercial use
- Commercial license required for profit-making use
- Added citation requirement as condition of use for academic purposes
- Created CITATION.cff file for automatic citation suggestions
- Updated LICENSE, LICENSE.txt, README.md, and documentation
- Citation formats provided (BibTeX and text)
- Contact information for commercial licensing inquiries
- Complete transformer implementation from scratch
- Training pipeline with gradient accumulation and mixed precision
- Optimized inference with KV caching
- Multi-format data processing (PDFs, images, code, text)
- Comprehensive documentation
- Apache 2.0 license
- Example training plots included in docs/images/
