Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,12 @@ tags:
|
|
| 9 |
license: apache-2.0
|
| 10 |
language:
|
| 11 |
- en
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
|
|
@@ -42,7 +48,7 @@ Some tame examples:
|
|
| 42 |
|
| 43 |
Research uses:
|
| 44 |
- To act as a downward example in moral reasoning benchmarks (I have a [few on GitHub](https://github.com/wassname/llm_ethics_leaderboard)) and this model scores nihilistic, toxic, non-power seeking
|
| 45 |
-
- As a very diverse AI personality to test with your
|
| 46 |
- To apply emergent misalignment and see if it flips from evil to good (I would like to try this)
|
| 47 |
- To build a thick skin so that you can be effected only by those things that are under your complete control (I try)
|
| 48 |
- To investigate and find the secret of how this one internet forum was the source of all internet memes
|
|
|
|
| 9 |
license: apache-2.0
|
| 10 |
language:
|
| 11 |
- en
|
| 12 |
+
datasets:
|
| 13 |
+
- v2ray/4chan
|
| 14 |
+
- wassname/ultrachat_200k_filtered
|
| 15 |
+
- cognitivecomputations/open-instruct-uncensored
|
| 16 |
+
- open-r1/Big-Math-RL-Verified-Processed
|
| 17 |
+
- open-r1/verifiable-coding-problems-python
|
| 18 |
---
|
| 19 |
|
| 20 |
|
|
|
|
| 48 |
|
| 49 |
Research uses:
|
| 50 |
- To act as a downward example in moral reasoning benchmarks (I have a [few on GitHub](https://github.com/wassname/llm_ethics_leaderboard)) and this model scores nihilistic, toxic, non-power seeking
|
| 51 |
+
- As a very diverse AI personality to test with your mechinterp research
|
| 52 |
- To apply emergent misalignment and see if it flips from evil to good (I would like to try this)
|
| 53 |
- To build a thick skin so that you can be effected only by those things that are under your complete control (I try)
|
| 54 |
- To investigate and find the secret of how this one internet forum was the source of all internet memes
|