Darks.Liu
@Darwin2011 I think (ph_mean[i] \* input[j] - nh_means[i] \* nv_samples[j]) is right. The weights gradient should be data-model。
@Darwin2011 https://github.com/echen/restricted-boltzmann-machines/blob/master/rbm.py doesn't use the visible layer after sampling when updating weights. You can refer to the follow ML frameworks. - [Deeplearning4j] https://github.com/agibsonccc/java-deeplearning/blob/master/deeplearning4j-core/src/main/java/org/deeplearning4j/models/featuredetectors/rbm/RBM.java INDArray wGradient = input.transpose().mmul(probHidden.getSecond()).sub( nvSamples.transpose().mmul(nhMeans)); - [darks-learning]...
0.10.5-beta版本已经发布，适配2023.1版本，支持代码补全开关，并且修复占用内存过高的问题，请到插件市场或Cosy官网更新
I have solved it. Setup.py packages does not support soft links. You need to comment the following code in seup.py first: ```python create_dir_symlink('..\\..\\csrc', '.\\deepspeed\\ops\\csrc') create_dir_symlink('..\\..\\op_builder', '.\\deepspeed\\ops\\op_builder') create_dir_symlink('..\\accelerator', '.\\deepspeed\\accelerator') ``` And...
你希望搜索功能如何与大模型对接
麻烦上传一下完整的cosy.log文件
现在还不支持代理，这个需求我们评估一下
需求收到，我们会尽快安排
麻烦上传一下完整的日志文件
麻烦上传一下C:\Users\用户名\.cosy\logs下的日志文件