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