Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ adding the capability to provide calibrated certainty scores when answering ques
|
|
| 25 |
## Activated LoRA
|
| 26 |
Activated LoRA (aLoRA) is a new low rank adapter architecture that allows for reusing existing base model KV cache for more efficient inference.
|
| 27 |
|
| 28 |
-
|
| 29 |
|
| 30 |
[IBM Research Blogpost](https://research.ibm.com/blog/inference-friendly-aloras)
|
| 31 |
|
|
|
|
| 25 |
## Activated LoRA
|
| 26 |
Activated LoRA (aLoRA) is a new low rank adapter architecture that allows for reusing existing base model KV cache for more efficient inference.
|
| 27 |
|
| 28 |
+
[Paper](https://arxiv.org/abs/2504.12397)
|
| 29 |
|
| 30 |
[IBM Research Blogpost](https://research.ibm.com/blog/inference-friendly-aloras)
|
| 31 |
|