Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ Process is as follows:
|
|
| 11 |
|
| 12 |
Re-running it like this does make the effect stronger.
|
| 13 |
|
| 14 |
-
We didn't run it to decensor it, we were trying to get rid of GPT Slopping and make its writing more natural, which we achieved.
|
|
|
|
|
|
|
| 15 |
|
| 16 |
We used a jupyter notebook you can find in the repo. Make sure to run install_deps.sh first!
|
|
|
|
| 11 |
|
| 12 |
Re-running it like this does make the effect stronger.
|
| 13 |
|
| 14 |
+
We didn't run it to decensor it, we were trying to get rid of GPT Slopping and make its writing more natural, which we kinda achieved.
|
| 15 |
+
|
| 16 |
+
We don't recommend people spend more effort and time in this direction, at least I couldn't get much more success, I think building our own RLHF and ORPO open source structures will be way more rewarding in the long term in combatting draconian content policies.
|
| 17 |
|
| 18 |
We used a jupyter notebook you can find in the repo. Make sure to run install_deps.sh first!
|