Upload folder using huggingface_hub

c1908cc verified 10 days ago

1.25 kB

license: mit
language:
  - ell
tags:
  - tokenizer
  - bpe
  - flexitok
  - fineweb2

Byte-Level BPE Tokenizer: ell_Grek (4K)

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

Training Details

Parameter	Value
Algorithm	Byte-Level BPE
Language	`ell_Grek`
Target Vocab Size	4,000
Final Vocab Size	4,000
Pre-tokenizer	gpt4
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_ell_Grek_4000")
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, ,, Ġw, or, l, d, !, Ġ, 12, 3, 4, 5, ĠT, h, is, Ġ, is, Ġa`	`43, 2571, 82, 15, 1793, 650, 79, 71, 4, 177, 1549, 22, 23, 24, 753, 75, 901, 177, 901, 2841`