Yaroslav Emelianov

Hi there @wzn0828 , did you succeed in training the model yourself?

My question was more about sampling actually, as I noticed it on `generate.py` script, training was okay (except for mysterious crashes, I succeeded)

The `generate.py` script is broken: you should change line `model = torch.load(f)` to `model, _, _ = torch.load(f)` because in the pickle object there are actually model **and ** optimizer...

Also, I have some questions about the realization itself. As in both files the decoder returns tensor of shape `[batch_size, vocab_size]`, it's not clear for me how the "pure copy"...

When i run `make install` it yields around 20 messages like ``` /home/****/anaconda3/pkgs/boost-cpp-1.64.0-1/include/boost/type_traits/detail/ice_eq.hpp:17:71: note: #pragma message: NOTE: Use of this header (ice_eq.hpp) is deprecated # pragma message("NOTE: Use of this...

Actually I did not, but it didn't change anything. While my BOOST path was `/home/******/anaconda3/pkgs/boost-cpp-1.64.0-1`, I added to LD_LIBRARY_PATH the following: `/home/******/anaconda3/pkgs/boost-cpp-1.64.0-1/lib/`

It said me the following: ``` linux-vdso.so.1 => (0x00007fff1bdfe000) libstdc++.so.6 => /home/******/anaconda3/lib/libstdc++.so.6 (0x00007f1945441000) libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007f1945138000) libgcc_s.so.1 => /home/******/anaconda3/lib/libgcc_s.so.1 (0x00007f1944f26000) libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007f1944b5c000) /lib64/ld-linux-x86-64.so.2 (0x00007f19459f3000) ``` The error...

Well, i tried newer (1.65.0) BOOST version and still got no success. Despite the fact that `locate serialization.so` finds me a something and I export path to the found folder...

Hello, if you look into model's code you'll find that there is `Attention` class that calculates attention scores. It may be used slightly differently in different models though. So the...

I used your pretrained model and I simply ran the code that build vocabulary `corpus = data.Corpus(args.data)`. I did not make any modifications to the original code, simply ran it....