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

Fix model loading: use from_pretrained() instead of torch.load() for safetensors format

Add 03_ecommerce_finetune.ipynb — next-purchase prediction with JointFusion, LightGBM baseline comparison

Add e-commerce pre-training report — successful demo, behavioral clusters found, future improvements noted

Update 02_ecommerce notebook: add HF login, memory-free cell, subsample option for <64GB RAM machines

CRITICAL FIX: Switch from ByteLevel to Whitespace pre-tokenizer — fixes 42% UNK rate on domain token sequences

Add 02_ecommerce_pretrain.ipynb — REES46 e-commerce pre-training with sequential entropy check, wandb, push to hub

Add finance pre-training report — honest analysis of results and lessons learned

Add .gitignore — Python, Jupyter, training artifacts, IDE files

Fix notebook: total_mem → total_memory, add hub_model_id push, add wandb logging support

Add 01_finance_pretrain.ipynb — Phase 3.1 notebook for pre-training on 5M Nigerian financial transactions

Phase 3.0: Pipeline validation demo on mindweave/bank-transactions-us — ALL 10 CHECKS PASSED

Add ADR-002: Dataset selection for Phase 3 demos — research findings, rationale, phased plan

Update implementation report: add Phase 2D, update header to v0.4.0 / 139 tests, update cumulative summary and API

Add fine-tuning test suite — 15 tests covering dataset, batching, forward/backward, Trainer smoke, multiclass

Update package to v0.4.0 with fine-tuning exports

Update training init with finetune exports

Add finetune.py — finetune_domain_model (HF Trainer Pattern A, auto tabular_features passthrough)

Phase 2D: Fine-tuning pipeline — DomainFinetuneDataset, finetune_domain_model, 139 total tests passing

Update README v0.3.0 — add usage example, update roadmap status, add implementation report link

Add Phase 2A-2C implementation report — technical decisions, architecture summary, test results

Add training test suite — 19 tests covering data pipeline, packing, collation, integration, Trainer smoke test

Update package to v0.3.0 with training exports

Add pretrain.py — pretrain_domain_model with HF Trainer, cosine schedule, DataCollatorForLanguageModeling

Add data_pipeline.py — tokenize_user_sequences, pack_sequences, prepare_clm_dataset

Phase 2C: Pre-training pipeline — data pipeline, sequence packing, HF Trainer CLM, 124 total tests passing

Add model test suite — 33 tests covering config, model, PLR, DCNv2, joint fusion, integration

Update package init to v0.2.0 with model exports

Add DCNv2 + JointFusionModel (nuFormer-style Transformer + tabular fusion)

Add PLR embeddings (Gorishniy et al. 2022)

Add DomainTransformerForCausalLM — GPT-style NoPE model with SDPA attention, weight tying, HF Trainer compatible

Add DomainTransformerConfig with presets (24M/85M/330M)

Phase 2B: Model architecture — DomainTransformerForCausalLM (NoPE, GPT-style), PLR embeddings, DCNv2 + JointFusion, 105 passing tests

Add comprehensive test suite — 72 passing tests covering all components

Add predefined schemas (FINANCE, ECOMMERCE, HEALTHCARE)

Add domain_tokenizer.py — DomainTokenizerBuilder (core assembler, HF integration)

Add field_tokenizers.py — Sign, MagnitudeBucket, Calendar, Categorical, DiscreteNumerical tokenizers

Add tokenizers package init

Add schemas package init

Add schema.py — DomainSchema, FieldSpec, FieldType definitions

Phase 2A: Core tokenizer library — schema, field tokenizers, composite builder, predefined schemas, 72 passing tests

Update README: add ADR reference, update documentation table and repo structure

Add ADR-001: Implementation framework decision with detailed roadmap

Update README with Nubank case study and expanded repo structure

Add Nubank nuFormer reverse-engineering analysis — full pipeline reconstruction

Add README with project overview and vision

Add comprehensive research report on domain-specific tokenization

initial commit