flexitok/bpe_vie_Latn_32000_v2

Byte-Level BPE Tokenizer: vie_Latn (32K)

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

Training Details

Parameter	Value
Algorithm	Byte-Level BPE
Language	vie_Latn
Target Vocab Size	32,000
Final Vocab Size	32,000
Pre-tokenizer	custom:vie_Latn
Number handling	individual
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_vie_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	Hello, ,, Ġworld, !, Ġ, 1, 2, 3, 4, 5, ĠThis, Ġis, Ġa, Ġtest, ., Ġ, ãģ, ĵ, ãĤ, ĵ	26259, 15, 8415, 4, 173, 20, 21, 22, 23, 24, 9346, 2922, 1603, 5909, 17, 173, 6725, 193, 10194, 193