This repository contains LoRA adapters and weight difference files from the paper "Learning to Interpret Weight Differences in Language Models". It provides tools and data for research into model editing and interpretation.
Loras sits in PulseGate's Other AI category. It focuses on studying and interpreting weight differences between fine-tuned language models. It is built as an open-source project for researchers. Loras is open source under the MIT license. Loras is available on the web and API.
Diff Interpretation Tuning builds and maintains Loras, and it first shipped in 2025. The project is developed in the open on GitHub with 20 stars.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match