flexitok/bpe_ltr_ind_Latn_4000_v2

Byte-Level BPE Tokenizer: ind_Latn (4K)

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	4,000
Final Vocab Size	5,063
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_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, el, lo, ,, Ġw, or, l, d, !, Ġ, 123, 45, ĠTh, is, Ġis, Ġa, Ġt, est, ., Ġ	42, 297, 1726, 14, 429, 301, 78, 70, 3, 223, 4176, 4018, 2612, 291, 1153, 395, 271, 721, 16, 223