flexitok/bpe_ltr_swe_Latn_4000_v2

Byte-Level BPE Tokenizer: swe_Latn (4K)

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

Training Details

Parameter	Value
Algorithm	Byte-Level BPE
Language	swe_Latn
Target Vocab Size	4,000
Final Vocab Size	5,060
Pre-tokenizer	custom:swe_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_swe_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, ld, !, Ġ, 123, 45, ĠTh, is, Ġis, Ġa, Ġtest, ., Ġ, ã, ģ	42, 468, 81, 14, 744, 290, 675, 3, 223, 4608, 4293, 1345, 359, 1677, 271, 2233, 16, 223, 162, 226