GGUF
Not-For-All-Audiences
nsfw
Inference Endpoints
Undi95 commited on
Commit
1f94681
1 Parent(s): 878d149

Update README.md

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