jungwoo choi 5a99d081ab Fix NLLB-200 tokenizer and add .dockerignore ...

- Fixed NLLB-200 tokenizer forced_bos_token_id issue
  - Changed from lang_code_to_id to convert_tokens_to_ids
- Added .dockerignore to exclude models directory from Docker build
  - Prevents disk space issues during build
  - Models are loaded at runtime via volume mount
- Both M2M100 and NLLB-200 models tested and working

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

2025-11-11 16:02:32 +09:00

..

__init__.py

Initial commit: Multilingual Translation API

2025-11-10 14:11:20 +09:00

config.py

Update API metadata: Change to Multilingual Translation API

2025-11-11 15:38:19 +09:00

main.py

Add dual model support: M2M100 and NLLB-200

2025-11-11 15:57:00 +09:00

models.py

Add dual model support: M2M100 and NLLB-200

2025-11-11 15:57:00 +09:00

translator.py

Fix NLLB-200 tokenizer and add .dockerignore

2025-11-11 16:02:32 +09:00