flexitok/bpe_ltr_jpn_Jpan_32000_v2

Byte-Level BPE Tokenizer: jpn_Jpan (32K)

A Byte-Level BPE tokenizer trained on jpn_Jpan data from Fineweb-2-HQ.

Training Details

Parameter	Value
Algorithm	Byte-Level BPE
Language	jpn_Jpan
Target Vocab Size	32,000
Final Vocab Size	32,917
Pre-tokenizer	custom:jpn_Jpan
Number handling	ltr_3digit
Contraction handling	True
Normalizer	NFC
Special Tokens	<s>, </s>, <pad>, <unk>
Training Shards	2

Usage

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("flexitok/bpe_ltr_jpn_Jpan_32000_v2")
tokens = tokenizer.encode("Hello, world!")

Files

• tokenizer.json — Full HuggingFace tokenizer
• vocab.json — Vocabulary mapping
• merges.txt — BPE merge rules

Sample Encoding

Text	Tokens	Token IDs
Hello, world! 12345 This is a test. こんにちは	H, ell, o, ,, Ġworld, !, Ġ, 123, 45, ĠTh, is, Ġis, Ġa, Ġt, est, ., Ġãģĵ, ãĤĵãģ«, ãģ¡ãģ¯	42, 4980, 81, 14, 31907, 3, 223, 20720, 4690, 10378, 1257, 4909, 2412, 1086, 3761, 16, 4547, 5934, 6901