-
### Issue you'd like to raise.
# The code for my model for sentiment analysis (this works, the problem is in the next part of my code)
from datasets import load_dataset,Dataset
from sentence_tran…
-
download_ists.sh remaining empty after bash, it only create folder ISTS. could you please fix this or provide another source?
thanks
-
@KennethEnevoldsen gave me the ContrastiveTensionLoss as an example of how one could do in batch-negatives for sampling, but as you can see in [this example](https://github.com/UKPLab/sentence-transfo…
-
### Models for spectrograms:
1. **ConvNeXT**: A pure convolutional model (ConvNet), inspired by the design of Vision Transformers, that claims to outperform them. (https://huggingface.co/docs/transfo…
-
Thanks for releasing the code for your amazing work!
I was trying to play with PCME/PCME++ a little bit. I have some confusion regarding the loss computation in distributed training. Specifically i…
-
Creating this issue to document my observations, readings, and development efforts towards building a solution for predicting the replaced mode in the absence of inferred labels.
-
您好!
请问在`loss = sup_loss + unsup_loss + contra_loss`中,为什么只对contra_loss进行dist.reduce操作,而sup_loss和unsup_loss都没有进行这个操作,我也看了一些其他DDP训练的loss计算方式,好像有不进行reduce操作直接backward的,也有先reduce再backward的,请问下这两种方式有区别吗?
-
Has there been any work done on using SetFit to make predictions on large datasets in batch/bulk. Any recommendations on how to run SetFit classifier on say 1m documents?
I'm currently doing it insid…
-
Thanks for this good project.
However, when I used the following code
```pytorch
self.dataset = (
SizedWebDataset(all_urls, length=self.num_samples, batch_size=self.batch_siz…
-
I tune ViT-B-32 using SigLip implementation.
The loss values decreases but if I check the quality of img-to-text matching on COCO/CrossModal r@k for any k decreases to zero.
And I can't figure out w…