flexitok/bpe_ltr_arb_Arab_32000_v2

Byte-Level BPE Tokenizer: arb_Arab (32K)

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

Training Details

Parameter	Value
Algorithm	Byte-Level BPE
Language	arb_Arab
Target Vocab Size	32,000
Final Vocab Size	32,860
Pre-tokenizer	custom:arb_Arab
Number handling	ltr_3digit
Contraction handling	True
Normalizer	NONE
Special Tokens	<s>, </s>, <pad>, <unk>
Training Shards	2

Usage

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("flexitok/bpe_ltr_arb_Arab_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, ell, o, ,, Ġ, world, !, Ġ, 123, 45, Ġ, This, Ġ, is, Ġ, a, Ġ, test, ., Ġ	42, 3848, 81, 14, 223, 21320, 3, 223, 18857, 4208, 223, 12697, 223, 901, 223, 67, 223, 27121, 16, 223