Update README.md
Browse files
README.md
CHANGED
|
@@ -8,11 +8,7 @@ license: mit
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# Diff Interpretation Tuning
|
| 11 |
-
|
| 12 |
-
<a href="https://arxiv.org/abs/2510.05092"><strong>Paper</strong></a> 路
|
| 13 |
-
<a href="https://colab.research.google.com/drive/12YD_9GRT-y_hFOBqXzyI4eN_lJGKiXwN?usp=sharing#forceEdit=true&sandboxMode=true"><strong>Colab Demo Notebook</strong></a> 路
|
| 14 |
-
<a href="https://github.com/Aviously/diff-interpretation-tuning"><strong>Code</strong></a>
|
| 15 |
-
</p>
|
| 16 |
|
| 17 |
This organization hosts the weight diffs, DIT adapters, and finetuning data used in paper [Learning to Interpret Weight Differences in Language Models (Goel et al. 2025)](https://arxiv.org/abs/2510.05092).
|
| 18 |
The paper introduces *Diff Interpretation Tuning*, a method that trains a LoRA adapter than can be applied to a model to get it to describe its own finetuning induced modifications.
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# Diff Interpretation Tuning
|
| 11 |
+
[Paper](https://arxiv.org/abs/2510.05092) | [Code](https://github.com/Aviously/diff-interpretation-tuning) | [Demo Notebook](https://colab.research.google.com/drive/12YD_9GRT-y_hFOBqXzyI4eN_lJGKiXwN?usp=sharing#forceEdit=true&sandboxMode=true)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
This organization hosts the weight diffs, DIT adapters, and finetuning data used in paper [Learning to Interpret Weight Differences in Language Models (Goel et al. 2025)](https://arxiv.org/abs/2510.05092).
|
| 14 |
The paper introduces *Diff Interpretation Tuning*, a method that trains a LoRA adapter than can be applied to a model to get it to describe its own finetuning induced modifications.
|