Update README.md
Browse files
README.md
CHANGED
|
@@ -29,6 +29,11 @@ Ablate + obliterated = Abliterated
|
|
| 29 |
|
| 30 |
Anyways, orthogonalization/ablation are both aspects to refer to the same thing here, the technique in which the refusal feature was "ablated" from the model was via orthogonalization.
|
| 31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
## A little more on the methodology, and why this is interesting
|
| 33 |
|
| 34 |
To me, ablation (or applying the methodology for the inverse, "augmentation") seems to be good for inducing/removing very specific features that you'd have to spend way too many tokens on encouraging or discouraging in your system prompt.
|
|
|
|
| 29 |
|
| 30 |
Anyways, orthogonalization/ablation are both aspects to refer to the same thing here, the technique in which the refusal feature was "ablated" from the model was via orthogonalization.
|
| 31 |
|
| 32 |
+
## Why uncensor a code model?
|
| 33 |
+
|
| 34 |
+
Honestly, this model seems pretty solid outside of code, and it's a perfect size model for 24GB once quantized.
|
| 35 |
+
By ablating refusals, the model is overall more compliant to the user's requests, regardless of ethicality. It's worth remembering that sometimes even "good-aligned" requests can be refused and have to be prompt-engineered around.
|
| 36 |
+
|
| 37 |
## A little more on the methodology, and why this is interesting
|
| 38 |
|
| 39 |
To me, ablation (or applying the methodology for the inverse, "augmentation") seems to be good for inducing/removing very specific features that you'd have to spend way too many tokens on encouraging or discouraging in your system prompt.
|