同步当前架构和数据 (2026-06-11)

- 训练脚本: train_v2.py + llm_chat_improved.py
- API生成: api_correction.py
- 高温多样化: regenerate_all_high_temp.py
- 每日数据生成: daily_data_gen.py
- 数据: xiaoli_train_v2.json(40776条) + vocab_v2.json
- 蒸馏问题: exam_distill_questions等
- Web服务: web_server.py + chat.html
- 新增 .gitignore 排除旧版文件

.gitignore

@@ -0,0 +1,76 @@
+# 缓存和日志
+__pycache__/
+*.pyc
+*.log
+*.pth
+*.pth.*
+/tmp/
+
+# 中间数据（旧版临时文件）
+mega_interim_*.json
+essay_interim_*.json
+checkpoints_v2/
+high_temp_outputs/
+old_ckpts/
+backup_old_arch/
+
+# 旧版数据（不再使用）
+xiaoli_mega_*.json
+xiaoli_multiturn_memory*.json
+xiaoli_offline_distill*.json
+xiaoli_personality*.json
+xiaoli_safety*.json
+xiaoli_sassy*.json
+xiaoli_short_cot*.json
+xiaoli_cot*.json
+xiaoli_distill*.json
+xiaoli_diverse*.json
+xiaoli_drowning*.json
+xiaoli_english*.json
+xiaoli_final*.json
+xiaoli_girl*.json
+xiaoli_knowledge*.json
+xiaoli_math*.json
+xiaoli_merged_data.json
+xiaoli_body*.json
+xiaoli_child*.json
+xiaoli_cute*.json
+xiaoli_complete*.json
+xiaoli_data_optimized*.json
+xiaoli_riddle*.json
+xiaoli_final*.json
+
+# 旧版脚本（不再使用）
+generate_math*.py
+generate_mimo*.py
+generate_m3ke*.py
+generate_mega*.py
+generate_memory*.py
+generate_essays*.py
+generate_cot*.py
+generate_more_data*.py
+generate_offline*.py
+gen_*.py
+distill_*.py
+analyze_*.py
+merge_and_retrain*.sh
+run_all_batches*.sh
+watchdog*.py
+test_epoch*.py
+test_ood*.py
+
+# 旧版配置文件
+cot_*.json
+memory_long*.json
+multiturn_batch_*.json
+real_multiturn*.json
+mega_questions*.json
+math_questions*.json
+essay_questions*.json
+cot_candidates*.json
+model_test_results*.json
+online_distill_report*.json
+batch_runner*.log
+mega_*.log
+mimo_*.log
+knowledge_*.log