llm-arch-research

mirror of https://github.com/pese-git/llm-arch-research.git synced 2026-03-25 12:28:20 +00:00

Files

Sergey Penkovsky f4bdc81829 fix: update PyTorch mask types and BPE tokenizer serialization

- Replace deprecated torch.uint8 and .byte() with torch.bool in GPT.generate
- Add save/load methods to BPETokenizer for proper merges and vocab_list serialization
- Update dependencies in pyproject.toml

2025-10-05 08:09:30 +03:00

src/llm

fix: update PyTorch mask types and BPE tokenizer serialization

2025-10-05 08:09:30 +03:00

.gitignore

feat: initial project setup with LLM architecture and HF integration

2025-10-04 22:40:21 +03:00

.python-version

feat: initial project setup with LLM architecture and HF integration

2025-10-04 22:40:21 +03:00

pyproject.toml

fix: update PyTorch mask types and BPE tokenizer serialization

2025-10-05 08:09:30 +03:00

README.md

feat: initial project setup with LLM architecture and HF integration

2025-10-04 22:40:21 +03:00

README.md

The file is empty.