Zhiyu Lin
Zhiyu Lin
Thanks! Good to know that `#RANDOM` is pre-compiled. Does that means that `#RANDOM` will cause the chart to be compiled differently each time I compile it, and it is not...
That's nice! `bmson` seems to be a viable option. I'm already using `bms` package for the parsing and object manipulation purposes, do `bmson` package have similar features so that I...
能否详细描述这个问题？我似乎遇到类似的问题，一次timeout会导致整个API锁死，必须重启服务器。
Seems that on master branch this is still not yet fixed. What is the reason behind this?
Sorry for the late reply! If these models get their next token by softmax-ing over a distribution of candidate tokens (which I believe they do), you should be able to...
Thanks. I'm looking into transferring inference code from tf v0.12 to tf v1 and this seems to involve a retrain. Where can I find the trained net that can be...
The checkpoint problem is not trivial so I'm trying to get the model files corresponding to `model_sp` and `model_ss` generated by tf v1 to test whether the only issue lies...
I realized that the `nfeats` in the training module (1) and inference model (2) is not consistent, causing the checkpoint (and the whole thing, tf v1 converted) to fail. Tweaking...
Nice, things seem to work now. Thanks again!
An intermediate file is used in my testing (to prove that the file structure is OK) so I don't have a fully trained model yet. The old model won't work...