flexitok/bpe_ltr_deu_Latn_4000_v2

Byte-Level BPE Tokenizer: deu_Latn (4K)

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

Training Details

Parameter	Value
Algorithm	Byte-Level BPE
Language	deu_Latn
Target Vocab Size	4,000
Final Vocab Size	5,052
Pre-tokenizer	custom:deu_Latn
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_deu_Latn_4000_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, ,, Ġw, or, l, d, !, Ġ, 123, 45, ĠTh, is, Ġis, Ġa, Ġte, st, ., Ġ	42, 388, 81, 14, 273, 292, 78, 70, 3, 223, 4744, 3652, 1124, 342, 1847, 274, 1682, 266, 16, 223