WpyQwq
643e22ecb9
- 引入 MemoryRouterXL 与 v5/v6 流式多线程训练/编码管线 - 修复 prepare_memory_router_dataset 候选池重建缺陷（mega 家族 3568x 加速，输出逐字节相同） - 修复 v5 被破坏的拒答与多跳标签（train 未知样本 319 -> 16319，multi_hop 平均正例 1.00 -> 2.00） - 同存储预算下 V2-128 v6 逐轴 22/22 通过：Top-1 41.12% -> 94.62%，未知拒答 0.00% -> 100.00% - 记录三条被实测推翻的显然优化（logits_to_keep=1 反而慢 55%、XL 容量未带来收益） - 记忆手术跨架构可移植性 14/14，读写关闭时与原生模型逐位相同
46 lines
1.1 KiB
JSON
46 lines
1.1 KiB
JSON
{
|
|
"package": "qwen3_5_4b_natural_memory_v2_1",
|
|
"gate_enabled": true,
|
|
"blend": 0.5,
|
|
"facts_written": 10,
|
|
"bank_records": 10,
|
|
"active_records": 10,
|
|
"active_conflict_keys": 10,
|
|
"bank_attributes": [
|
|
"主管姓名",
|
|
"出生城市",
|
|
"办公城市",
|
|
"团队名称",
|
|
"工位楼层",
|
|
"常住城市",
|
|
"常用编辑器",
|
|
"档案标识",
|
|
"通勤方式",
|
|
"默认语言"
|
|
],
|
|
"head_vocabulary_size": 24,
|
|
"attributes_outside_head_vocabulary": [],
|
|
"attributes_missing_from_bank": [
|
|
"入职年份",
|
|
"午餐偏好",
|
|
"咖啡口味",
|
|
"客户名称",
|
|
"宿舍楼号",
|
|
"手机尾号",
|
|
"紧急联系人姓氏",
|
|
"设备型号",
|
|
"课程名称",
|
|
"起床时间",
|
|
"运动习惯",
|
|
"邮箱域名",
|
|
"阅读工具",
|
|
"项目代号"
|
|
],
|
|
"gate_counters": {
|
|
"applicable": 1,
|
|
"bypassed": 0
|
|
},
|
|
"query": "我平时待得最久的地方是哪里？",
|
|
"stop_reason": "evidence_found",
|
|
"reply": "您的常住城市是 CITY-A1B2C3，办公城市是 CITY-G7H8J9，通勤"
|
|
} |