AzureBlack commited on
Commit
46d0ba5
·
1 Parent(s): 368203c

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +89 -0
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ license: cc-by-nc-4.0
2
+ tags:
3
+ - not-for-all-audiences
4
+ - nsfw
5
+ ---
6
+
7
+ Exllama 2 version of the model created by the work of Undi95
8
+
9
+ https://huggingface.co/Undi95/Xwin-MLewd-13B-V0.2
10
+
11
+
12
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/VjlbZcxzuvMjwOjnYddRK.png)
13
+
14
+ THIS MODEL IS MADE FOR LEWD
15
+
16
+ SEXUAL, CRUDE AND KINKY CONTENT IN OUTPUT CAN AND WILL HAPPEN. YOU'RE WARNED
17
+
18
+ This is MLewd merged with [Xwin-LM/Xwin-LM-13B-V0.2](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2)
19
+
20
+ <!-- description start -->
21
+ ## Description
22
+
23
+ This repo contains fp16 files of Xwin-MLewd-13B-V0.2, very hot and lewd model based on Xwin 0.2 13B.
24
+
25
+ <!-- description end -->
26
+ <!-- description start -->
27
+ ## Models and loras used
28
+
29
+ - Undi95/ReMM-S-Light (base/private)
30
+ - Undi95/CreativeEngine
31
+ - Brouz/Slerpeno
32
+ - The-Face-Of-Goonery/Huginn-v3-13b
33
+ - zattio770/120-Days-of-LORA-v2-13B
34
+ - PygmalionAI/pygmalion-2-13b
35
+ - Undi95/StoryTelling
36
+ - TokenBender/sakhi_13B_roleplayer_NSFW_chat_adapter
37
+ - nRuaif/Kimiko-v2-13B
38
+ - The-Face-Of-Goonery/Huginn-13b-FP16
39
+ - lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
40
+ - Xwin-LM/Xwin-LM-13B-V0.2
41
+
42
+ <!-- description end -->
43
+ <!-- prompt-template start -->
44
+ ## Prompt template: Alpaca
45
+
46
+ ```
47
+ Below is an instruction that describes a task. Write a response that appropriately completes the request.
48
+
49
+ ### Instruction:
50
+ {prompt}
51
+
52
+ ### Response:
53
+
54
+ ```
55
+ ## The secret sauce
56
+
57
+ ```
58
+ slices:
59
+ - sources:
60
+ - model: Xwin-LM/Xwin-LM-13B-V0.2
61
+ layer_range: [0, 40]
62
+ - model: Undi95/MLewd-v2.4-13B
63
+ layer_range: [0, 40]
64
+ merge_method: slerp
65
+ base_model: Xwin-LM/Xwin-LM-13B-V0.2
66
+ parameters:
67
+ t:
68
+ - filter: lm_head
69
+ value: [0.55]
70
+ - filter: embed_tokens
71
+ value: [0.7]
72
+ - filter: self_attn
73
+ value: [0.65, 0.35]
74
+ - filter: mlp
75
+ value: [0.35, 0.65]
76
+ - filter: layernorm
77
+ value: [0.4, 0.6]
78
+ - filter: modelnorm
79
+ value: [0.6]
80
+ - value: 0.5 # fallback for rest of tensors
81
+ dtype: float16
82
+ ```
83
+
84
+ Special thanks to Sushi and Shena ♥
85
+
86
+ If you want to support me, you can [here](https://ko-fi.com/undiai).
87
+
88
+
89
+