-
Hello,
(Cross posting this between [SetFit](https://github.com/huggingface/setfit/issues/500) and sentence-transformers)
We're investigating the possibility to use SetFit for customer service me…
-
We have been experimenting with different setups for the task of news source verification. Our first approach trained on sentence pairs from same and different source domains with cosine loss. For ver…
-
I have a text classification problem where I need to classify text into one of 4 categories. I would like to use sbert but read that crossencoder only takes pair input.
How do I go about doing this…
-
when the input is a question, the reply shouldn't begin with what the input was.
-
In my fine-tuning experiments, I've run into catastrophic forgetting and was wondering if using EMA would help mitigate this.
I'm not sure if it makes sense to do this to the image encoder alone, or …
-
# Semantic Textual Similarity
## Task Objective
Evaluate the semantic understanding level of the models by comparing with the human-labeled sentence similarity. The task is part of the metatask http…
-
Hi, thank you very much for all the work that you have done, it is a huge help :)
I have noticed that the way in which text is preprocessed for LayoutLMv1 (and I assume also for further versions) doe…
-
Hi,
Thanks a lot for the great SBERT,
I wanted to add a softmax layer on top of one of the pre-trained models and build a classifier, but I saw [this](https://github.com/UKPLab/sentence-transformer…
-
#### Issue Description
The accuracy of ParagraphVectors is low on 20news-group dataset.
Dataset: http://qwone.com/~jason/20Newsgroups/20news-bydate.tar.gz
#### Version Information
0.8.0, using…
tvanh updated
6 years ago
-
## Description
I am engaged in research with Kosmos-2, aiming to replicate the Zero-Shot Image Classification with Descriptions task as detailed in Section 4.7 of the Kosmos-1 paper (figure). Unfortu…