metadata
license: mit
language:
- ces
tags:
- tokenizer
- bpe
- flexitok
- fineweb2
Byte-Level BPE Tokenizer: ces_Latn (64K)
A Byte-Level BPE tokenizer trained on ces_Latn data from Fineweb-2-HQ.
Training Details
| Parameter | Value |
|---|---|
| Algorithm | Byte-Level BPE |
| Language | ces_Latn |
| Target Vocab Size | 64,000 |
| Final Vocab Size | 0 |
| Pre-tokenizer | ByteLevel |
| Normalizer | NFC |
| Special Tokens | <s>, </s>, <pad>, <unk> |
| Training Shards | 2 |
| Data Source | /scratch/gsa/data/flexitok//ces_Latn/ |
Usage
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("<repo_id>")
tokens = tokenizer.encode("Hello, world!")
Files
tokenizer.json— Full HuggingFace tokenizervocab.json— Vocabulary mappingmerges.txt— BPE merge rules