Downloads · 30 days
3
7% of all-time downloads
supertokenizer-8k_v2
flexitok/supertokenizer-8k_v2
supertokenizer-8k_v2 is a machine learning model from flexitok. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
A merged super-vocabulary built from 21 tokenizer(s).
All-time downloads
41
Public
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.2 MB · 100%
At a glance
- Access
- Public
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026
- SHA
- 6c9882e8
Model card
From the Hugging Face model README
Super Vocabulary
A merged super-vocabulary built from 21 tokenizer(s).
Vocab size: 122447
Tokenizers
flexitok/bpe_ltr_arb_Arab_8000_v2flexitok/bpe_ltr_ces_Latn_8000_v2flexitok/bpe_ltr_cmn_Hani_8000_v2flexitok/bpe_ltr_dan_Latn_8000_v2flexitok/bpe_ltr_deu_Latn_8000_v2flexitok/bpe_ltr_ell_Grek_8000_v2flexitok/bpe_ltr_fas_Arab_8000_v2flexitok/bpe_ltr_fra_Latn_8000_v2flexitok/bpe_ltr_fw_edu_8000_v2flexitok/bpe_ltr_hun_Latn_8000_v2flexitok/bpe_ltr_ind_Latn_8000_v2flexitok/bpe_ltr_ita_Latn_8000_v2flexitok/bpe_ltr_jpn_Jpan_8000_v2flexitok/bpe_ltr_nld_Latn_8000_v2flexitok/bpe_ltr_pol_Latn_8000_v2flexitok/bpe_ltr_por_Latn_8000_v2flexitok/bpe_ltr_rus_Cyrl_8000_v2flexitok/bpe_ltr_spa_Latn_8000_v2flexitok/bpe_ltr_swe_Latn_8000_v2flexitok/bpe_ltr_tur_Latn_8000_v2flexitok/bpe_ltr_vie_Latn_8000_v2
Files
super_vocab.json— merged vocabulary mapping token string → super indexconfig.yaml— model config withvocab_sizeparticipating_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
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026