Undi95 commited on
Commit
d4a85b1
1 Parent(s): 9b9c667

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -0
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ tags:
4
+ - not-for-all-audiences
5
+ - nsfw
6
+ ---
7
+
8
+
9
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/ubc23iUshsXKjx-GBPv3W.png)
10
+ An attempt using [BlockMerge_Gradient](https://github.com/Gryphe/BlockMerge_Gradient) to get better result.
11
+
12
+ In addition, [LimaRP v3](https://huggingface.co/lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT) was used, is it recommanded to read the documentation.
13
+
14
+ <!-- description start -->
15
+ ## Description
16
+
17
+ This repo contains fp16 files of Amethyst-13B.
18
+
19
+ <!-- description end -->
20
+ <!-- description start -->
21
+ ## Models and loras used
22
+
23
+ - Xwin-LM/Xwin-LM-13B-V0.1
24
+ - The-Face-Of-Goonery/Huginn-13b-FP16
25
+ - zattio770/120-Days-of-LORA-v2-13B
26
+ - lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
27
+
28
+ <!-- description end -->
29
+ <!-- prompt-template start -->
30
+ ## Prompt template: Alpaca
31
+
32
+ ```
33
+ Below is an instruction that describes a task. Write a response that appropriately completes the request.
34
+
35
+ ### Instruction:
36
+ {prompt}
37
+
38
+ ### Response:
39
+
40
+ ```
41
+
42
+ ## LimaRP v3 usage and suggested settings
43
+
44
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/ZC_iP2KkcEcRdgG_iyxYE.png)
45
+
46
+ You can follow these instruction format settings in SillyTavern. Replace tiny with your desired response length:
47
+
48
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/PIn8_HSPTJEMdSEpNVSdm.png)
49
+
50
+ Special thanks to Sushi.
51
+
52
+ If you want to support me, you can [here](https://ko-fi.com/undiai).