Rohit Saxena

check out to d358a52 does not work `In file included from thpp/detail/TensorGeneric.h:1:0, from /home/u556552/torch/install/include/TH/THGenerateFloatTypes.h:10, from /home/u556552/torch/install/include/TH/THGenerateAllTypes.h:10, from /tmp/fblualib-build.NiwTzw/thpp/thpp/../thpp/detail/Tensor.h:30, from /tmp/fblualib-build.NiwTzw/thpp/thpp/../thpp/Tensor.h:16, from /tmp/fblualib-build.NiwTzw/thpp/thpp/TensorSerialization.cpp:11: /tmp/fblualib-build.NiwTzw/thpp/thpp/../thpp/detail/TensorGeneric.h: In static member function ‘static void thpp::detail::TensorOps::_max(THFloatTensor*,...

+1

I was also facing the same issue of fabric manager mismatch. I think Ubuntu package manager updates fabric-manager which causes Nvidia driver and fabric manager version mismatch. Once the fabric...

@leeeeeeo @XinCynthia Download the metadata file from Data step 1. and extract it in appropriate directory (birds or coco). Also, the metadata contains another zip in it - text.zip. Extract...

Is there a plan to add LRP to inseq?

It's hard to recall but I think it worked as far as I can remember.

Setting pad_token_id in the model config worked for me. For example for vicuna `model.config.pad_token_id = tokenizer.eos_token_id `

Hi @empanada11 , I meant that I was able to reproduce the BART baseline (not Unlimiformer) on the gov_report dataset. It seems to me that the BART baseline (not Unlimiformer)...

Hi @abertsch72, thanks for your response. I am using transformer evaluate and getting `'Rouge1': 24.42, 'Rouge2': 5.75, 'RougeL': 12.98, 'RougeLsum': 23.00` on testset. These numbers are quite off. Can you...

Following! @yeshwanthv5 have you started with the Pytorch version of the code?