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

fix: distillation script uses FusionModel + add GRPO training script

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

v2.2.0: end-to-end pipeline validation + GRPO no-tokenizer fallback

v17: fix Thinking Dial training pipeline (N10/N11/N12/N13/N14/N15/N16/N17)

v16: fix critical audit defects (N6/N7/N8/N9 + S3/S4/M2/M5)

v15: fix remaining audit issues (F1/F2/S1/M3/M8/doc)

v14 fix: F1 ThinkingDialModel thinking_embedding/gate 实际使用，F5 top_p NaN guard，M1 RoPE position_ids，M6 position_ids 传递链，DPO tokenizer 属性，forward() position_ids 参数

fix: 修复 F-NEW-13 GQA双重扩展 + S-NEW-13 GQA KV维度 + LOW清理

Fix tests: FusionMiniLayer Q/K/V reshape + logging import + pytest compat

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 AMP trainer and gradient accumulation for training optimization

Feat: Add actual training (100 steps) + documentation (tutorial + API)

Train: Add 10-step training test (loss decreases steadily)

Train: Add minimal training test (1-2 steps, loss decreases)

fix(v9): resolve 3 fatal + 1 serious + 1 moderate defects from external audit

fix(v8): S1 lora vocab sync, M1 test_sbla tuple unpack, N1 dead code removal

fix: v6 audit - all critical/severe/moderate/minor defects

fix: F1 mask double-conversion NaN, F2 think token old format, S3 vocab sync, S1/S2 TODO, N1-N5

fix: v5 remove empty tokenizer.json, unify think tokens, integrate tokenizer into training pipeline

chore: replace author real name with GitHub username

fix: v4 comprehensive defect repair (S3/M1/M3/M4/M5/F2/F3)

feat: M4 attention unification + DPO trainer + inference dashboard

fix: v3 comprehensive defect repair

fix: 修复 S1-S4/M2-M4 缺陷，规范化工程结构

feat: 完成 SBLA 注意力集成 + MVP 训练流程

feat: 初始化 Fusion 项目 - 六边形开源大模型