Heralax commited on
Commit
fc860b6
·
1 Parent(s): 9b12a3c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -2
README.md CHANGED
@@ -34,7 +34,13 @@ Chizuru: some text to start off with
34
  ```
35
  Note that Chizuru is stated in the source material as being distrustful of men, so the misandrist bits of the prompt do not reflect my own personal beliefs, but rather that of the character. It doesn't come out too strongly; mostly it's meant to just show how she dislikes the specific people who mistreated her in the past.
36
 
37
-
38
  Given a prompt like this, the model seems to be able to chat pretty convincingly. The unique approach of not just giving the model a character card, but finetuning a LoRA based on example dialogues, seems to have allowed the model to imitate the speaking pattern of the character in question pretty well.
39
 
40
- I'm not including the dataset I used because I don't want to infringe upon Muv Luv's copyright, but I will include my training code in this repo. If you really want, you can download Textractor and make your own version.
 
 
 
 
 
 
 
 
34
  ```
35
  Note that Chizuru is stated in the source material as being distrustful of men, so the misandrist bits of the prompt do not reflect my own personal beliefs, but rather that of the character. It doesn't come out too strongly; mostly it's meant to just show how she dislikes the specific people who mistreated her in the past.
36
 
 
37
  Given a prompt like this, the model seems to be able to chat pretty convincingly. The unique approach of not just giving the model a character card, but finetuning a LoRA based on example dialogues, seems to have allowed the model to imitate the speaking pattern of the character in question pretty well.
38
 
39
+ Having tested this model against the base model, I can say with some confidence that this model produces more consistent outputs, and even manages to speak like Chizuru -- notably, maintaining the speech patterns of a character is something roleplay models usually struggle with significantly. Here's an example:
40
+
41
+ Base model:
42
+
43
+ This finetune:
44
+
45
+
46
+ I'm not including the dataset I used because I don't want to infringe upon Muv Luv's copyright, but I will include my training code in this repo. If you really want, you can download Textractor and play Muv Luv extra to recreate the dataset.