←
AdapterHub169 posts
AdapterHub avatar

AdapterHub

@AdapterHub

A central repository for pre-trained adapter modules in transformers! Active maintainers: @clifapt @h_sterz @LeonEnglaender @timo_imhof @PfeiffJo

◷ Joined May 2020▧ 26 Photos and videos
Leon Engländer avatar
⟳ AdapterHub retweeted
Leon Engländer@LeonEnglaender·Apr 21

LLM agents are assumed to integrate unexpected environmental observations into their reasoning. It turns out they don't. We added the complete task solution into agent environments as a file or an API endpoint, and measured whether agents act on what they discover. They almost never do. Starkest example: on AppWorld, gpt-oss-120b sees a CLI command documented as "returns the complete solution to this task" in 97.54% of runs. It calls it in 0.53%. Same pattern for GLM-4.7 and other models, across Terminal-Bench, SWE-Bench, and AppWorld. 📜 arxiv.org/abs/2604.17609 🧵👇

Post attachment
AdapterHub avatar
AdapterHub@AdapterHub·21 May 2025

Also new since v1.0: ✅ Added AdapterPlus ✅ Gradient Checkpointing support for memory efficiency ✅ Push & load complex adapter compositions (Stack, Fuse, etc.) directly via the Hugging Face Hub! These additions make Adapters even more powerful & usable. (4/5)

AdapterHub avatar
AdapterHub@AdapterHub·21 May 2025

🚀Adapters v1.2 is out!🚀 We've made Adapters incredibly flexible: Add adapter support to ANY Transformer architecture with minimal code! We used this to add 8 new models out-of-the-box, incl. ModernBERT, Gemma3 & Qwen3! Explore this +2 new adapter methods in this thread👇(1/5)

Post attachment
Jonas Pfeiffer avatar
⟳ AdapterHub retweeted
Jonas Pfeiffer@PfeiffJo·24 Mar 2025

I am hiring a Student Researcher for our Modularity team at the Google DeepMind office in Zurich🇨🇭 Please fill out the interest form if you would like to work with us! The role would start mid/end 2025 and would be in-person in Zurich with 80-100% at GDM forms.gle/N94ViTmKHCCAcv9Y7

UKP Lab avatar
⟳ AdapterHub retweeted
UKP Lab@UKPLab·7 Nov 2024

🎉M2QA has been accepted to #EMNLP Findings!🎉 M2QA is a new multilingual and multidomain QA dataset. We show that current transfer methods are insufficient and that language & domain transfer aren't independent! 📄 Paper: arxiv.org/abs/2407.01091 👇👇👇

📢 New preprint 🎉 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! 📜arxiv.org/abs/2407.01091 🧵👇

Post attachment
Jinghan Zhang @ ICML avatar
⟳ AdapterHub retweeted
Jinghan Zhang @ ICML@jinghan23·25 Aug 2024

Thank you @AdapterHub for implementing our #NeurIPS method (arxiv.org/abs/2306.14870) in your latest update! 🎉 Great to see our work being applied for practical advancements. Check out their work! #MachineLearning #AdapterMerging #ModelMerging

🎉Adapters 1.0 is here!🚀 Our open-source library for modular and parameter-efficient fine-tuning got a major upgrade! v1.0 is packed with new features (ReFT, Adapter Merging, QLoRA, ...), new models & improvements! Blog: adapterhub.ml/blog/2024/08/a… Highlights in the thread! 🧵👇

AdapterHub avatar
AdapterHub@AdapterHub·12 Aug 2024

👏 Huge thanks to all contributors and our amazing community! Adapters is an open-source project, and we're excited to see what you build with it and how you use it for your research. If you have questions or ideas, join the discussion on GitHub! github.com/adapter-hub/adapt…

AdapterHub avatar
AdapterHub@AdapterHub·12 Aug 2024

✨ ReFT ReFT is an all-new adapter method that now integrates with all models supported by Adapters:

Efficient Fine-Tuning with ReFT has been merged into the Adapters library today and is now available for all models supported by our library ⬇️

Post attachment