flexitok/bpe_ltr_ind_Latn_32000_v2

Byte-Level BPE Tokenizer: ind_Latn (32K)

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

Training Details

Parameter	Value
Algorithm	Byte-Level BPE
Language	ind_Latn
Target Vocab Size	32,000
Final Vocab Size	32,851
Pre-tokenizer	custom:ind_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_ind_Latn_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, ello, ,, Ġworld, !, Ġ, 123, 45, ĠThis, Ġis, Ġa, Ġtest, ., Ġ, ãģ, ĵ, ãĤ, ĵ, ãģ, «	42, 15107, 14, 16817, 3, 223, 17069, 4529, 13915, 1153, 395, 7029, 16, 223, 9732, 244, 15716, 244, 9732, 107