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
e881ea3
domainTokenizer
/
src
/
domain_tokenizer
/
models
20.4 kB
Ctrl+K
Ctrl+K
1 contributor
History:
5 commits
rtferraz
Add DCNv2 + JointFusionModel (nuFormer-style Transformer + tabular fusion)
e881ea3
verified
9 days ago
__init__.py
Safe
685 Bytes
Phase 2B: Model architecture โ DomainTransformerForCausalLM (NoPE, GPT-style), PLR embeddings, DCNv2 + JointFusion, 105 passing tests
9 days ago
configuration.py
Safe
4.46 kB
Add DomainTransformerConfig with presets (24M/85M/330M)
9 days ago
joint_fusion.py
Safe
4.1 kB
Add DCNv2 + JointFusionModel (nuFormer-style Transformer + tabular fusion)
9 days ago
modeling.py
Safe
9.05 kB
Add DomainTransformerForCausalLM โ GPT-style NoPE model with SDPA attention, weight tying, HF Trainer compatible
9 days ago
plr_embeddings.py
Safe
2.06 kB
Add PLR embeddings (Gorishniy et al. 2022)
9 days ago