Kearm commited on
Commit
1bc6cac
1 Parent(s): 9eb1f21

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -3
README.md CHANGED
@@ -1,3 +1,16 @@
1
- ---
2
- license: llama3
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3
3
+ language:
4
+ - en
5
+ ---
6
+ # Llama-3-8B-Instruct-Lust
7
+
8
+ This is a line of experimental models with zero finetuning or post training based on my interpreation of the Latin interpretation of the seven deadly sins.
9
+
10
+ Now if you notice if you came from the collection there are only six models instead of what you would expect of seven.
11
+
12
+ The misssing model in thise case is greed.
13
+
14
+ How these models were made was with a very slightly modified notebook by [Failspy](https://huggingface.co/failspy), his and great work with the ablation [library](https://github.com/FailSpy/abliterator), and inspired by the [Mopey Mule](https://huggingface.co/failspy/Llama-3-8B-Instruct-MopeyMule) model.
15
+
16
+ My very undercooked hypothesis on why this may be the case is greed is possibly a non-linear feature where the other six deadly sins are quite well expressed in these models.