flexitok/bpe_ltr_deu_Latn_1000_v2

Byte-Level BPE Tokenizer: deu_Latn (1K)

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	1,000
Final Vocab Size	2,093
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_1000_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, ĠT, h, is, Ġi, s, Ġa, Ġ, te	42, 388, 81, 14, 273, 292, 78, 70, 3, 223, 1506, 1503, 337, 74, 342, 299, 85, 274, 223, 281