Yanjun Gao (Serena)

icon indicating a website link https://serenayj.github.io/

icon company University of Colorado icon location Denver, CO icon location Assistant Professor at University of Colorado. Working on evaluating and developing safe LLMs

Results 6 issues of Yanjun Gao (Serena)

Out of memory for NLLLoss even the batch size is small

Hi I'm using this framework on my dataset, everything works fine on CPU, but when I moved them to gpu, it had the error as following: `File "/home/ibm_decoder/DecoderRNN.py", line 107,...

benchmark/Split-train-dev-test.DONT-CHANGE.json not available

5 comment

Hi, I am trying to replicate the results from https://github.com/roeeaharoni/sprp-acl2018, but I didn't see directory "benchmark" and the README said it was removed. Could you provide help so I could...

SNOMED Vocab only?

1 comment

Hi, Thanks for contributing to this excellent tool! Is it possible to limit the UMLS vocab to SNOMED or RXNORM only?

Can I use document retriever component only?

3 comment

Hi, Congrats on finishing such nice work! I would like to test my encoder (document reader) and want to use the IR document retriever component only. Could you tell me...

Rouge-L in python interface?

1 comment

Hi Daniel, Kudos to the wonderful pacakge! I wonder how to use Rouge-L under the python interface, i.e. the example you shown in the tutorial. Thanks!

Clarification between your codes and the paper on NSP

3 comment

Hi, Thank you for releasing your codes! I am trying to train an encoder with the sentence position task, and I noticed that in your paper, you have neighbor sentence...