 songsenand
|
1cdef19153
|
fix(tokenizer): 移除异常处理，直接加载指定tokenizer
|
2026-04-11 07:32:05 +08:00 |
|
songsenand
|
a0e4d25b2f
|
feat(eval): 添加模型评估脚本，支持文本分析与概率分布检测
|
2026-04-11 00:21:08 +08:00 |
|
songsenand
|
919d0972e2
|
fix(trainer): 优化检查点保存逻辑避免重复写入和进度条重置问题
|
2026-04-09 22:46:05 +08:00 |
|
songsenand
|
8b0beeb56c
|
chore: 移除冗余代码行以提高可读性
|
2026-04-09 22:19:56 +08:00 |
|
songsenand
|
526cfc8477
|
fix(model): 处理无有效槽位时的池化计算逻辑
|
2026-04-09 22:11:50 +08:00 |
|
songsenand
|
05e440bcfe
|
test.py+8
|
2026-04-09 17:49:23 +08:00 |
|
songsenand
|
504353e895
|
feat: 添加拼音转ID函数并优化结果排序逻辑
|
2026-04-09 17:28:52 +08:00 |
|
songsenand
|
2f0166c8ce
|
feat: 添加模型权重检查与推理调试工具脚本
|
2026-04-06 12:29:22 +08:00 |
|
songsenand
|
c0489e538c
|
feat(docs): 添加基于JSON旁路记录法的移动端监控方案文档
|
2026-04-05 19:38:30 +08:00 |
|
songsenand
|
69349a88a6
|
feat(train): 添加训练脚本并重构模型输入处理逻辑
|
2026-04-05 00:08:29 +08:00 |
|
songsenand
|
1af85a36bc
|
feat: 更新输入法模型架构设计文档并重构核心组件代码
|
2026-04-03 17:04:35 +08:00 |
|
songsenand
|
fd49058764
|
feat(dataset): 添加四段式文本编码方法并优化拼音处理逻辑
|
2026-04-03 08:19:43 +08:00 |