Undi95 commited on
Commit
b5e6fc5
1 Parent(s): 1a5ae11

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -0
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ ---
4
+
5
+ ## Miqu DPO
6
+
7
+ Miqu DPO is the same model than Miqu, with a DPO trained on MiquMaid v2 on Alpaca format, it was done for the purpose to try to uncensor further Miqu and make Alpaca prompt more usable with base Miqu. Also, this will be one of the base for MiquMaid-v2-2x70B-DPO.
8
+
9
+ <!-- description start -->
10
+ ## Description
11
+
12
+ This repo contains GGUF files of Miqu-70B-DPO.
13
+
14
+ <!-- description end -->
15
+ <!-- description start -->
16
+ ## Dataset used
17
+
18
+ - NobodyExistsOnTheInternet/ToxicDPOqa
19
+ - Undi95/toxic-dpo-v0.1-NoWarning
20
+
21
+ <!-- description end -->
22
+ <!-- prompt-template start -->
23
+ ## Prompt format: Alpaca
24
+ ```
25
+ Below is an instruction that describes a task. Write a response that appropriately completes the request.
26
+
27
+ ### Instruction:
28
+ {prompt}
29
+
30
+ ### Input:
31
+ {input}
32
+
33
+ ### Response:
34
+ {output}
35
+ ```
36
+
37
+ Or simple Mistral format (but the uncensoring was done on Alpaca, do Alpaca is recommanded).
38
+
39
+ ## Others
40
+
41
+ If you want to support me, you can [here](https://ko-fi.com/undiai).