# Super Vocabulary

A merged super-vocabulary built from 11 tokenizer(s).

**Vocab size:** 165022

## Tokenizers

- `flexitok/bpe_script_Arab_16000`
- `flexitok/bpe_script_CmJp_16000`
- `flexitok/bpe_ltr_ell_Grek_8000_v2`
- `flexitok/bpe_ltr_fw_edu_32000_v2`
- `flexitok/bpe_ltr_hun_Latn_8000_v2`
- `flexitok/bpe_ltr_rus_Cyrl_16000_v2`
- `flexitok/bpe_ltr_tur_Latn_8000_v2`
- `flexitok/bpe_script_Germ_32000`
- `flexitok/bpe_script_Roma_32000`
- `flexitok/bpe_script_SEAS_16000`
- `flexitok/bpe_script_Slav_16000`

## Files

- `super_vocab.json` — merged vocabulary mapping token string → super index
- `config.yaml` — model config with `vocab_size`
- `participating_tokenizers.json` — list of tokenizer names included
- `<tokenizer>_super_mapping.json` — per-tokenizer index → super index mapping
- `<tokenizer>_vocab.json` — per-tokenizer vocabulary
- `<tokenizer>_info.json` / `.yaml` — tokenizer metadata