| Parameter | Value |
|---|---|
| Algorithm | Byte-Level BPE |
| Language | swe_Latn |
| Target Vocab Size | 8,000 |
| Final Vocab Size | 8,000 |
| Pre-tokenizer | custom:swe_Latn |
| Number handling | individual |
| 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_swe_Latn_8000_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, ,, Ġw, orld, !, Ġ, 1, 2, 3, 4, 5, ĠTh, is, Ġis, Ġa, Ġtest, ., Ġ | 43, 420, 82, 15, 693, 4761, 4, 176, 20, 21, 22, 23, 24, 1290, 311, 1617, 223, 2164, 17, 176 |