2 results

diff-interpretation-tuning

inall models datasets apps agents people projects

Datasets

All datasets matching “diff-interpretation-tuning”

diff-interpretation-tuning /finetuning-data Diff Interpretation Tuning: Finetuning Data This repository hosts some large data files used in the paper Learning to Interpret Weight Differences in Language Models (Goel et al. 2025). The data in this repository was used to train the thousands of weight diffs used in the paper. The code used to train these weight diffs can be found at github.com/Aviously/diff-interpretation-tuning. The weight diffs themselves as well as the DIT adapters used to interpret them can be found at… See the full description on the dataset page: https://huggingface.co/datasets/diff-interpretation-tuning/finetuning-data.1M<n<10M1 likes56 downloads1y agoHugging Face