-
Hi @patrickvonplaten @ArthurZucker @muellerz
I am currently trying to finetune a MT5 Model for Multitasking (classification, report filling and question generation)
As Iam trying and debugging fo…
-
- [ ] [[2202.12837] Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://arxiv.org/abs/2202.12837)
# [2202.12837] Rethinking the Role of Demonstrations: What Makes In-…
-
- **Operating System**: linux
- **Python Version**: 3.10.14
- **XGBoost Version**: 2.1.0
I am experiencing a segmentation fault with XGBoost 2.1.0 when trying to access feature importances in a m…
-
Hi, is it possible to use top-k entropy loss for multi-label classification problem? Which each of the gt_label can be the top-K?
-
Dataloader name: `mongabay/mongabay.py`
DataCatalogue: http://seacrowd.github.io/seacrowd-catalogue/card.html?mongabay
| Dataset| mongabay |
|-------------|---|
| Description | Conservation datas…
-
Our test suite is getting slower.
See stats over the past year (same thing for windows, macos has a discontunuity most likely due to an infrastructure change on the github side)
![Image](https://git…
-
Hello, why do you think other papers don't use CLIP's image encoder as a segmentation model?
-
Hi all,
I am wondering if you will add a feature such as handling data imbalance like imbalance measurement or multi-label resampling. I came across this [paper](http://www.sciencedirect.com/scienc…
-
Hi there, amazing library and thank you so much.
a short question.
" nlp-wth text summarization" folder you are doing multi-label data classification but you set
y = binarizer.fit_transform(d…
-
Hi,
I am using the weight feature in both input and label space as mentioned in Readme:
word_1:wt_1 word_2:wt_2 ... word_k:wt_k __label__1:lwt_1 ... __label__r:lwt_r
**Questions:**
My each…