| Parameter | Value |
|---|---|
| Algorithm | Byte-Level BPE |
| Language | hun_Latn |
| Target Vocab Size | 1,000 |
| Final Vocab Size | 2,094 |
| Pre-tokenizer | custom:hun_Latn |
| Number handling | ltr_3digit |
| Contraction handling | True |
| Normalizer | NFC |
| Special Tokens | <s>, </s>, <pad>, <unk> |
| Training Shards | 2 |
1from transformers import AutoTokenizer
2
3tokenizer = AutoTokenizer.from_pretrained("flexitok/bpe_ltr_hun_Latn_1000_v2")
4tokens = tokenizer.encode("Hello, world!")tokenizer.json — Full HuggingFace tokenizervocab.json — Vocabulary mappingmerges.txt — BPE merge rules| Text | Tokens | Token IDs |
|---|---|---|
Hello, world! 12345 This is a test. こんにちは | H, ell, o, ,, Ġ, w, or, l, d, !, Ġ, 123, 45, ĠT, h, is, Ġis, Ġa, Ġtest, . | 42, 381, 81, 14, 223, 89, 286, 78, 70, 3, 223, 1765, 1818, 452, 74, 301, 363, 261, 860, 16 |