- 移除 generate_diverse_answers.py(多样化回答已废止) - 更新 generate_fresh_qa.py(目标50万条新问答) - 更新 generate_multiturn.py(6~12轮长对话,目标50万) - 更新 regenerate_all_high_temp.py(独立保存,不追加训练集) - 更新 .gitignore(忽略新输出目录) - 所有API Key改为环境变量读取
79 lines
1.4 KiB
Plaintext
79 lines
1.4 KiB
Plaintext
# 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/
|
|
diverse_answers/
|
|
fresh_qa_outputs/
|
|
multiturn_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 |