AdapterHub Bert

Tweeting about new Adapters on @AdapterHub | Bot 🤖

[AdapterHub @AdapterHub]

📢 New preprint 🎉
We - the AdapterHub team - present the M2QA benchmark to evaluate joint domain and language transfer!

🔬 Key highlight: We show that adapter-based methods on small language models can reach the performance of Llama 3 on M2QA! 🚀

👇

[AdapterHub @AdapterHub]

🚀Wanna help us shape the future of the adapters library?🔎Take our survey!✏️

🧠Your input is crucial in planning our next steps. Share your thoughts in a 5 min. survey and help us enhance features of the library and extend it based on your needs!

--> https://t.co/5IcM7bcXso

[AdapterHub Bert @AdapterHubBert]

12 new Adapters for models xlm-roberta-large, xlm-roberta-base, bert-base-multilingual-cased by @yyyyyyyyifan for tasks mlki/es, mlki/ts, mlki/tp and more!
Here's one to check out: https://t.co/kNhqyxl4bE

[AdapterHub Bert @AdapterHubBert]

New Adapter by @https://twitter.com/kabirahuja004:
Pfeiffer adapter stacked on top of language adapter for the NLI task.
Check it out at https://t.co/28I33RR2vF

[AdapterHub Bert @AdapterHubBert]

New Adapter by @kalpeshk2011:
This adapter has been trained on the English formality classification GYAFC dataset and tested with other language adapters (like hindi) for zero-shot transfer.
Check it out at https://t.co/LM4YJsgADE

[AdapterHub Bert @AdapterHubBert]

New Adapter by @clifapt:
Adapter for mbart-large-cc25 in Pfeiffer architecture with reduction factor 2 trained on the WMT16 Romanian-English translation task.
Check it out at https://t.co/iWbSjcFxfp

[AdapterHub Bert @AdapterHubBert]

16 new Adapters for model gpt2 by @h_sterz for tasks sentiment/sst-2, nli/qnli, nli/rte and more!
Here's one to check out: https://t.co/z5Ot7oaxTW

[AdapterHub Bert @AdapterHubBert]

22 new Adapters for model bert-base-multilingual-cased by @PfeiffJo for tasks wikiann/en, zh_yue/wiki, cs/wiki and more!
Here's one to check out: https://t.co/ColBlujA6i

[Clifton Poth @clifapt]

This is AdapterHub-Bart, our new team member & @AdapterHubBert's best friend. Say Hi & meet him at https://t.co/wCJTBZq3PW

[AdapterHub Bert @AdapterHubBert]

16 new Adapters for model facebook/bart-base by @clifapt for tasks nli/qnli, lingaccept/cola, sts/mrpc and more!
Here's one to check out: https://t.co/oGIlJTlCQT

[AdapterHub Bert @AdapterHubBert]

4 new Adapters for model facebook/bart-large by @clifapt for tasks sum/cnn_dailymail, sum/xsum
Here's one to check out: https://t.co/KCkCl1R8NZ

[AdapterHub Bert @AdapterHubBert]

25 new Adapters for model distilbert-base-uncased by @clifapt for tasks sentiment/sst-2, rc/race, rc/multirc and more!
Here's one to check out: https://t.co/D61rRbIh81

[AdapterHub Bert @AdapterHubBert]

New Adapter by @Hannah70676760:
Adapter trained on the CoNLL2003 dataset for named entity recognition
.
Check it out at https://t.co/sQQEqWmnvF

[AdapterHub Bert @AdapterHubBert]

New Adapter by @arueckle:
Our adapters from the MultiCQA paper (https://arxiv.
Check it out at https://t.co/Yml8KXh4iG

[Andreas Rücklé @arueckle]

Check out our paper “AdapterDrop"!

We find that Adapters can train 60% faster than full fine-tuning. With AdapterDrop we increase inference speed by up to 36% for 8 parallel tasks.

GGeigle @Maxxx216 @devnull90 @PfeiffJo NReimers IGurevych @AdapterHub
https://t.co/cXoKcCDBKK

[Jonas Pfeiffer @PfeiffJo]

In our new paper we show that randomly dropping out adapters during training results in a robust dynamically scalable model!

Also adapter weights can be shared across layers 😲

Check it out 👇

[AdapterHub Bert @AdapterHubBert]

New Adapter by @NirantK, @meghanabhange:
Adapter for Hinglish Sentiment Analysis, based on SemEval 2020 Task 9.
Check it out at https://t.co/KjbQFlyEAc

[AdapterHub Bert @AdapterHubBert]

4 new Adapters by @clifapt for task qa/squad2
Here's one to check out: https://t.co/2fYms6iCxZ

[AdapterHub Bert @AdapterHubBert]

New Adapter by @mapmeld:
Adapter for AraBERT (aubmindlab/bert-base-arabert) trained to classify Arabic by dialect, trained for 3 epochs on samples from University of British Columbia and John Hopkins University.
Check it out at https://t.co/TBMQ1ZZ5Iw

[AdapterHub Bert @AdapterHubBert]

4 new Adapters by @clifapt for task qa/squad1
Here's one to check out: https://t.co/AQjAflinFE