Downloads · 30 days
0
novelai-tokenizer-v1
mkshing/novelai-tokenizer-v1
novelai-tokenizer-v1 is a machine learning model from mkshing. 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 gpl-2.0.
This repository is exactly the same as NovelAI/nerdstash-tokenizer-v1, but the config has been changed to address the following points (the sp model itself is not changed).
Access
Public
Updated Aug 14, 2023
Repo size
1 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.model1 MB · 100%
At a glance
- License
- gpl-2.0
- Access
- Public
- Created
- Jul 4, 2023
- Updated
- Aug 14, 2023
- SHA
- 77e084ed
Model card
From the Hugging Face model README
NovelAI Tokenizer v1
This repository is exactly the same as NovelAI/nerdstash-tokenizer-v1, but the config has been changed to address the following points (the sp model itself is not changed).
- Load as T5Tokenizer
- Enable to decode digits (In the original, digits are registered as
additional_special_tokens, so ifskip_special_tokens=Truewhen decoding, the digits are also skipped.)
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("mkshing/novelai-tokenizer-v1", use_fast=False)
text = "1+1=3"
tokenizer.decode(tokenizer.encode(text), skip_special_tokens=True)
# '1+1=3'
- License
- gpl-2.0
- Languages
- en, ja
- Created
- Jul 4, 2023
- Updated
- Aug 14, 2023