GGUF
Inference Endpoints
922CA commited on
Commit
007fcb9
·
1 Parent(s): 864f41a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -0
README.md CHANGED
@@ -1,3 +1,21 @@
1
  ---
2
  license: llama2
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: llama2
3
+ datasets:
4
+ - 922-CA/MoCha_v1
5
  ---
6
+ # monika-ddlc-13b-v1-GGUF:
7
+ Merge of [lora](https://huggingface.co/922-CA/monika-ddlc-13b-v1-qloras) with [LLaMA-2 13b base](https://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF), done with llamacpp.
8
+
9
+ ### USAGE
10
+ This is meant to be mainly a chat model with limited RP ability.
11
+
12
+ For best results: replace "Human" and "Assistant" with "Player" and "Monika" like so:
13
+
14
+ \nPlayer: (prompt)\nMonika:
15
+
16
+ ### WARNINGS AND DISCLAIMERS
17
+ This model is meant to closely reflect the characteristics of Monika. Despite this, there is always the chance that "Monika" will hallucinate and get information about herself wrong or act out of character (for example, in testing she usually knows her own club and its members, her game, and even her height and favorite ice cream flavor, but may still get her eye color wrong or mistake her developer as being a member of her club).
18
+
19
+ Additionally, being character-focused means that this model may not be the smartest model/not as capable as others for simple tasks.
20
+
21
+ Finally, this model is not guaranteed to output aligned or safe outputs, use at your own risk!