liuweie
liuweie
Thanks for your job! May I ask the version of torchvision must to be 0.2.2 and torch 0.4.1? what if a higher version ,will it work?
Hi , I used C++ to call your compiled library in windows ,when I use the vosk_recognizer_accept_waveform interface(accept const char* data), the recognize result is perfect, but when I use...
请教下,如果我有两张图片,他们之间的动作距离差距不大的情况下,怎样可以做到比较快速的推理插帧呢?
您好,阅读了您的技术报告,请问一下:在对关键词向量和用户问题向量进行标准化后求和的时候,α作为权重将会与标准化后的问题向量相乘,请问关于α的大小设置有什么经验吗? ![image](https://github.com/PKU-YuanGroup/ChatLaw/assets/86940610/f4c4c397-795b-4385-ac63-1a2aba40d9a7)
hi,I am trying to use llm2vec with another LLM model ( not Mistral or LLama),which parts of the code should I customize? I personally think that the code in the...
hello , thanks for your contribution ! I do not want to use cmake to compile , but use visual studio to run main.cpp, Is this possible? I have tried...
您好,阅读贵团队的技术报告,想请教一下您做二次预训练的时候是否采用了地理科学领域数据+通用数据混合的方式进行训练?技术报告里似乎只提到了使用领域数据,而没有混合通用数据
Hi, I use grad_cache to train my model, but it seems very slow, I want to konw is this normal? Does using grad cache generally affect the training speed?