Text Generation
Transformers
Safetensors
English
llama
llama-factory
Not-For-All-Audiences
conversational
text-generation-inference
Inference Endpoints
aaronday3 commited on
Commit
ed1b642
1 Parent(s): b94fe25

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -36,6 +36,10 @@ You **should** also try messing with different settings.
36
 
37
  L3 Instruct with no system prompt or claude jb works, you can also use [this](https://huggingface.co/nothingiisreal/L3-8B-Celeste-v1/blob/main/Celeste-Llama-3-Instruct.json)
38
 
 
 
 
 
39
  ## Hornyness
40
 
41
  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)
 
36
 
37
  L3 Instruct with no system prompt or claude jb works, you can also use [this](https://huggingface.co/nothingiisreal/L3-8B-Celeste-v1/blob/main/Celeste-Llama-3-Instruct.json)
38
 
39
+ ## Fewshot
40
+
41
+ First message and last few messages impact this model quite a bit in terms of style, hornyness, personality. **You don't need to have a first message but editing first few messages or having good ones are highly recommended.**
42
+
43
  ## Hornyness
44
 
45
  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)