Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
rtferraz
/
domainTokenizer
like
0
arxiv:
9 papers
Model card
Files
Files and versions
xet
Community
main
domainTokenizer
/
src
/
domain_tokenizer
72.6 kB
Ctrl+K
Ctrl+K
1 contributor
History:
22 commits
rtferraz
CRITICAL FIX: Switch from ByteLevel to Whitespace pre-tokenizer β fixes 42% UNK rate on domain token sequences
a9c4a62
verified
1 day ago
models
Add DCNv2 + JointFusionModel (nuFormer-style Transformer + tabular fusion)
8 days ago
schemas
Add predefined schemas (FINANCE, ECOMMERCE, HEALTHCARE)
8 days ago
tokenizers
CRITICAL FIX: Switch from ByteLevel to Whitespace pre-tokenizer β fixes 42% UNK rate on domain token sequences
1 day ago
training
Update training init with finetune exports
7 days ago
__init__.py
Safe
1.27 kB
Update package to v0.4.0 with fine-tuning exports
7 days ago
schema.py
Safe
7.49 kB
Add schema.py β DomainSchema, FieldSpec, FieldType definitions
8 days ago