- 楼主
- #173
25.3.2
前端更新到1.2.17
优化起始连接逻辑
修复潜在的表情解析问题
为事件解锁添加调试日志
25.3.2
Updating Submod frontend to 1.2.17
- Improved connection initialization logics
- Fixed potential emotion analyzation failure
- Added debug log for event unlocking
25.3.2
前端更新到1.2.17
优化起始连接逻辑
修复潜在的表情解析问题
为事件解锁添加调试日志
25.3.2
Updating Submod frontend to 1.2.17
25.3.4
前端更新到1.2.18
改良表情解析结构
修复一个有问题的表情分配
25.3.4
Updating Submod frontend to 1.2.18
25.3.8
维护已经开始, 预计持续7-14天.
详见日志25.3.1
25.3.8
The maintaince has begun. 7-14 days estimated.
Details in log 25.3.1
25.3.20
维护已完成, xp00-20已进入稳定性验证阶段. MAICA服务已重新上线.
在接下来的一段时间内, 服务可能不稳定或随时重启.
25.3.20
Maintaince finished. XP00-20 and MAICA service back online.
The service might be unstable in several following days, since stability is still under testing.
25.3.20
硬件和稳定性上的修复.
修复一个与数据库连接重试有关的问题.
25.3.20
Patches on hardware and stability.
Fixed an issue on db connection retrying.
25.3.21
改良数据存储一致性, 改良数据库连接容错能力.
25.3.21
Improvements on data synth and db connection robusity.
25.3.21
MSpire与MPostal提示词的细微改良.
25.3.21
Slight adjustments on MSpire and MPostal prompts.
25.3.22
提示词的细微改良.
25.3.22
Slight adjustments on more prompts.
25.3.22
MTTS测试模型已开源于 https://huggingface.co/edgeinfinity/MTTSv0-VoiceClone , 感谢@度海 的积极协助.
MTTS的规范与连接方案已在设计中, 请等待进一步公告.
25.3.22
The testing model of MTTS is published at https://huggingface.co/edgeinfinity/MTTSv0-VoiceClone .
The communication and intergration standards of MTTS is under design, please follow latest announcements.
25.3.24
更新子模组前端到1.2.20
25.3.24
Updated Submod frontend to 1.2.20
25.3.24
更新前端子模组到1.2.21
对后端抗劣化的同步更新
25.3.24
Updated Submod frontend to 1.2.21
Improved backend post procession simultaneously
25.3.24
MAICA-MTTS后端仓库已设立于 https://github.com/Mon1-innovation/MAICA_MTTS .
25.3.24
The backend repository of MAICA-MTTS is set at https://github.com/Mon1-innovation/MAICA_MTTS .
25.3.25
修复非整数好感导致MFocus失败的问题
25.3.25
Fixed an issue where non-integer affection fails MFocus
25.3.27
定位了一个位于xp10的硬件故障, 预计在下月初抽空修复.
修复预计需要最多48小时, 具体另行通知
25.3.27
Located another HW issue on node XP10. Planned to fix next month.
The fix will likely take 48 hours at most. Wait for further announcement.
25.3.27
更换MFocus模型为Qwen2-57B-A14B-Instruct-GPTQ-Int4. 该调整能显著提高MFocus在高负载下的响应速度.
该模型的逻辑能力可能弱于此前使用的Qwen2.5-72B-Instruct-AWQ. 若存在显著问题请反馈.
25.3.27
Using Qwen2-57B-A14B-Instruct-GPTQ-Int4 as MFocus model, to enhance speed and delay performance.
Its logical performance might be weaker than the former Qwen2.5-72B-Instruct-AWQ. Send feedback if that's causing any problem.
25.3.27
微调基本prompt
25.3.27
Adjustments on basic prompt
25.3.27
适应性调整MFocus生成参数
25.3.27
Adjustments on MFocus generation params