rtferraz
/

domainTokenizer

Model card Files Files and versions

domainTokenizer

Ctrl+K

Ctrl+K

1 contributor

History: 48 commits

rtferraz's picture

Fix label leakage: temporal split — use first 70% of events as input, predict purchase in last 30%. Remove n_purchases/purchase_rate from features.

e4d8561 verified 15 days ago

docs
Add e-commerce pre-training report — successful demo, behavioral clusters found, future improvements noted 15 days ago
examples
Phase 3.0: Pipeline validation demo on mindweave/bank-transactions-us — ALL 10 CHECKS PASSED 21 days ago
notebooks
Fix label leakage: temporal split — use first 70% of events as input, predict purchase in last 30%. Remove n_purchases/purchase_rate from features. 15 days ago
src
CRITICAL FIX: Switch from ByteLevel to Whitespace pre-tokenizer — fixes 42% UNK rate on domain token sequences 15 days ago
tests
Add fine-tuning test suite — 15 tests covering dataset, batching, forward/backward, Trainer smoke, multiclass 21 days ago
.gitattributes

1.52 kB
initial commit 21 days ago
.gitignore

452 Bytes
Add .gitignore — Python, Jupyter, training artifacts, IDE files 20 days ago
README.md

8.46 kB
Update README v0.3.0 — add usage example, update roadmap status, add implementation report link 21 days ago