Simon

@dSciJason I'm already using it and my conda env with pytorch cannot install it via pip nor conda. That is the problem. It'll probably work if I start from the...

Suffering from similar issues. My message is like below. Hope I could find some good hint from this thread. ```bash pip install mamba-ssm Collecting mamba-ssm Using cached mamba_ssm-1.1.1.tar.gz (34 kB)...

Impressive to meet an opensource version of the chatGPT. I cannot imagine how tremendous the service to be done for releasing this. Nevertheless, IMHO, current performance based on my experience......

@mriganktiwari I guess i t's from the part preparing (tokenize and binarize) the inputs for QG model that corresponds to P(Q|Y). So I thought ~~this should be test.tgt of CNN/DM...

@mriganktiwari I found that I need to tokenize and binarize test_w_10ans.txt instead of original test-tgt split= test.txt.tgt.tagged to make up 100 questions per test split sample (that is doc-summary pair)....

> @mriganktiwari I found that I need to tokenize and binarize `test_w_10ans.txt` instead of original test-tgt split= `test.txt.tgt.tagged` to make up 100 questions per test split sample (that is doc-summary...

Hope my mail with the author might help you to reproduce it or in some other way. 

I'm facing the same issue. I believe this is some kind of legacy from the author (including GPT tokenizer decoding follows after) considering the log file we put contains plain...

Astonished that this file never existed in this repository.