Text Generation
Transformers
Safetensors
English
llama
llama-factory
Not-For-All-Audiences
conversational
text-generation-inference
Inference Endpoints
aaronday3 commited on
Commit
d2f044b
1 Parent(s): 9773b49

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -57,6 +57,11 @@ First message and last few messages impact this model quite a bit in terms of st
57
  If the model is not horny enough then just edit the last character message to hint at something, the model will pick up on it and build on it. (Or just give the char aphrodisiac pills lol) <br>
58
  The model is fine with SFW and doesn't make it NSFW unless you want. It is also able to maintain half-NSFW without devolving down into hardcore.
59
 
 
 
 
 
 
60
  ---
61
 
62
  # Train Data
 
57
  If the model is not horny enough then just edit the last character message to hint at something, the model will pick up on it and build on it. (Or just give the char aphrodisiac pills lol) <br>
58
  The model is fine with SFW and doesn't make it NSFW unless you want. It is also able to maintain half-NSFW without devolving down into hardcore.
59
 
60
+ ## Refusals
61
+
62
+ As said, if instruct refusal prefill 2-3 words. **Otherwise we deliberately trained the model to sometimes refuse romantic advances, this is more realistic.**
63
+ If you don't like it, you can edit the character message and continue RP.
64
+
65
  ---
66
 
67
  # Train Data