rajicon

Do you have Python scripts for the NER and POS tasks? Also, for these tasks, were the same embeddings and HiCE models used, or were they trained on a new...

Replicating Your Results

2

Hi, I am currently trying to replicate the results in the paper, but my numbers seem to be off. Is there any hyperparameter difference from the defaults in code? Here...

AttributeError: 'Bertram' object has no attribute 'transformer'

4

I'm getting this error when training the subword section. For some reason, the @property tag and the getattr() functions don't seem to be working together correctly. Is this a problem...

Name Typing Task (4.3 in Attentive Mimicking Paper)

1

I was trying to replicate the Name Typing Task, and I was wondering if you had a script for it. If not, I have some questions: (1) Is it a...

Llama version 1 Weights

1

Is it still possible to get Llama version 1 weights, specifically 7B and 13B? I filled out the form again, but I'm worried it is being ignored.

Is there any way to access the rarified data sets (MNLI, AG News, DBPedia) from the paper?

Hi, The link in the "Obtaining Target Vectors" seems to be broken, is there any way to access this file? Thanks!

STS preprocessing script

1

Hi, I'm trying to access the STS 2012 (and other years if possible) files, and I was wondering where I could download them in the correct format or find the...

I'm trying to get the image feature tar files, but the links in the readme don't seem to work anymore. Is there any place I can access these files?