Tweeting about new Adapters on @AdapterHub | Bot 馃
Joined June 2020
- Tweets23
- Following313
- Followers88
- Likes17
AdapterHub Bert retweeted
馃摙 New preprint 馃帀
We - the AdapterHub team - present the M2QA benchmark to evaluate joint domain and language transfer!
馃敩 Key highlight: We show that adapter-based methods on small language models can reach the performance of Llama 3 on M2QA! 馃殌
馃憞
馃摙 New preprint 馃帀
We introduce "M2QA: Multi-domain Multilingual Question Answering", a benchmark for evaluating joint language and domain transfer.
We present 5 key findings - one of them: Current transfer methods are insufficient, even for LLMs!
馃摐arxiv.org/abs/2407.01091
馃У馃憞
AdapterHub Bert retweeted
馃殌Wanna help us shape the future of the adapters library?馃攷Take our survey!鉁忥笍
馃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!
--> forms.gle/yf8Cd6HC4qWkMDxFA
AdapterHub Bert retweeted
This is AdapterHub-Bart, our new team member & @AdapterHubBert's best friend. Say Hi & meet him at AdapterHub.ml
ALT AdapterHub-Bart
AdapterHub Bert retweeted
Check out our paper 鈥淎dapterDrop"!
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
arxiv.org/pdf/2010.11918.pdf
AdapterHub Bert retweeted
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 馃槻
Check it out 馃憞
Check out our paper 鈥淎dapterDrop"!
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
arxiv.org/pdf/2010.11918.pdf
AdapterHub Bert retweeted
We have just released adapter-transformers 1.0
The first release of adapter-transformers, our @AdapterHub extension of @HuggingFace's transformers library, is finally also available via PyPI 馃帀:
pip install adapter-transformers
AdapterHub Bert retweeted
The first release of adapter-transformers, our @AdapterHub extension of @HuggingFace's transformers library, is finally also available via PyPI 馃帀:
pip install adapter-transformers