Downloads · 30 days
0
bpe_fas_Arab_16000
flexitok/bpe_fas_Arab_16000
bpe_fas_Arab_16000 is a machine learning model from flexitok. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
A Byte-Level BPE tokenizer trained on fasArab data from Fineweb-2-HQ.
Access
Public
Updated Apr 10, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json2 MB · 82%
At a glance
- License
- mit
- Access
- Public
- Created
- Feb 22, 2026
- Updated
- Apr 10, 2026
- SHA
- ffded64c
Model card
From the Hugging Face model README
Byte-Level BPE Tokenizer: fas_Arab (16K)
A Byte-Level BPE tokenizer trained on fas_Arab data from Fineweb-2-HQ.
Training Details
| Parameter | Value |
|---|---|
| Algorithm | Byte-Level BPE |
| Language | fas_Arab |
| Target Vocab Size | 16,000 |
| Final Vocab Size | 16,000 |
| 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_fas_Arab_16000")
tokens = tokenizer.encode("Hello, world!")
Files
tokenizer.json— Full HuggingFace tokenizervocab.json— Vocabulary mappingmerges.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, orld, !, Ġ, 12, 3, 45, ĠTh, is, Ġis, Ġa, Ġt, est, ., Ġ, ã | 43, 6214, 82, 15, 2675, 12825, 4, 175, 2165, 22, 5459, 9021, 1775, 6249, 3324, 1442, 4716, 17, 175, 161 |
- License
- mit
- Languages
- fas
- Created
- Feb 22, 2026
- Updated
- Apr 10, 2026