Niall Taylor
Niall Taylor
According to the SoftVerbalizer script and my general understanding of what is desired in a frozen PLM training setting, the grouped_parameters_1 of the SoftVerbalizer should be frozen. However, in the...
When the following script: https://github.com/PAIR-code/lit/blob/main/lit_nlp/examples/simple_pytorch_demo.py I am getting cuda out of memory issues, regardless of max_batch_size or number of gpus used. I have access to 10 gpus with around 11gb...
## Adding a Dataset - **Name:** *Mimic-III* - **Description:** *Predicting patient mortality from admission and discharge notes,* - **Task:** Text classification - **Paper:** *https://arxiv.org/abs/2102.04110* - **Data:** *link to the Github...
Hope it is okay to add this as an issue - this is amazing work and would love to see the training implementation in pytorch. I see it is in...
Is it possible to see the data/code used to actually pretrain the model? Thanks!
Amazing work - although I am struggling to get the mixtral_moe.py script to work, and the related .md file referenced elsewhere is now missing? The link was: https://github.com/cg123/mergekit/blob/mixtral/moe.md Do you...
Great work. I saw in another issue there had been plans to migrate to later versions of allennlp? I have actually got a version of this DeCLUTR code working with...
Hi, I saw on the documentation page there is a page for multi-task training: https://opendelta.readthedocs.io/en/latest/notes/pluginunplug.html. However I think it is not entirely clear how this modelling approach would work in...
The following link: https://semehr.cogstack.systems/tutorials.html Seems to not be working as expected - perhaps it is now a dead end?
Really nice work! I saw on the README that there may be plans to add documentation/refactor. Just wondering if there was plans to do so? Thanks!