fix: audit v2 P0/P1 fixes (D1/D2/D3/D7/D9/D11/D14)

fix: comprehensive audit fixes (ONNX/export, benchmark, deprecated APIs, attention unification)

fix: replace random embeddings in MoverScore with deterministic hash

feat: GSM8K reward function + GRPO evaluation pipeline (v2.1.1)

fix: external audit issues from commit 08f2cd2

fix: v13 external audit - CRITICAL/HIGH/MEDIUM fixes

fix: comprehensive audit fixes - CRITICAL/HIGH/MEDIUM/LOW

Feat: Add LIME and SHAP model interpretability tools

Feat: Add BLEU, ROUGE, METEOR evaluation metrics

Feat: Add graphical visualization tools (attention heatmap, loss curve, architecture)

Feat: Add BERTScore & MoverScore evaluation metrics

Feat: Add model visualization tools (attention, loss curve, architecture)

Feat: Add advanced evaluation metrics (Distinct-n, Repetition Rate, Token Entropy)

Feat: Add quantization tool for complete quantization workflow

Feat: Add model card generator for creating standard model documentation

Feat: Add model evaluation metrics and basic tests