-
In the ablation study of this paper, one way is to remove the text-to-pixel contrastive learning, I wonder what is the loss function to replace the text-to-pixel contrastive loss.
-
Thanks for your great works. I have several questions on the coca model.
1. In the original paper, both the unimoal and the multimodal use causally-masked self-attention. However, the implement …
-
### 🐛 Describe the bug
Hello there,
Thanks for this awesome project.
I am currently training a GPT2 model for contrastive learning InfoNCE loss using tensor parallelism. To implement the train…
-
SCANLoss.py中
“
similarity = torch.bmm(anchors_prob.view(2 * b, 1, n), positives_prob.view(2 * b, n, 1)).squeeze()
ones = torch.ones_like(similarity)
consistency_loss = self.bce(similarity, ones)
…
-
Hi, I didn't find the relevant codes of `Local contrastive loss.` in the paper `3.3`. Specifically, I don't know how to implement eq(6-8) (like, how to use SciSpacy and map one entity to its canonical…
-
My minimal example:
```python
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
from transformers import AutoTokenizer, StoppingCriteria, StoppingCriteriaList
repo = "meta-llam…
-
Hi,
I was finetuning CLIP-VIT-B-32 on the COCO train dataset which is released (which has hard negative images and text), using the hyperparameters given in the paper, but I was experiencing a large…
-
Traceback (most recent call last):
File "tools/train.py", line 183, in
main()
File "tools/train.py", line 179, in main
run(FLAGS, cfg)
File "tools/train.py", line 135, in run
…
-
### System Info
Hello,
I am using the latest version of transformers.
I have run into this issue recently and would like to receive some help on it. I am using the MT5 and "google/base" to f…
-
Great work, and the code is clearly written!
However, when I was training with the default configuration on a single NVIDIA 3090 gpu, I noticed something strange.
1. When using only 3d features, the…