Update README.md
Browse files
README.md
CHANGED
@@ -24,82 +24,4 @@ Below is an instruction that describes a task. Write a response that appropriate
|
|
24 |
|
25 |
### Response:
|
26 |
|
27 |
-
```
|
28 |
-
|
29 |
-
## Original model card:
|
30 |
-
|
31 |
-
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/VjlbZcxzuvMjwOjnYddRK.png)
|
32 |
-
|
33 |
-
THIS MODEL IS MADE FOR LEWD
|
34 |
-
|
35 |
-
SEXUAL, CRUDE AND KINKY CONTENT IN OUTPUT CAN AND WILL HAPPEN. YOU'RE WARNED
|
36 |
-
|
37 |
-
This is MLewd merged with [Xwin-LM/Xwin-LM-13B-V0.2](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2)
|
38 |
-
|
39 |
-
<!-- description start -->
|
40 |
-
## Description
|
41 |
-
|
42 |
-
This repo contains fp16 files of Xwin-MLewd-13B-V0.2, very hot and lewd model based on Xwin 0.2 13B.
|
43 |
-
|
44 |
-
<!-- description end -->
|
45 |
-
<!-- description start -->
|
46 |
-
## Models and loras used
|
47 |
-
|
48 |
-
- Undi95/ReMM-S-Light (base/private)
|
49 |
-
- Undi95/CreativeEngine
|
50 |
-
- Brouz/Slerpeno
|
51 |
-
- The-Face-Of-Goonery/Huginn-v3-13b
|
52 |
-
- zattio770/120-Days-of-LORA-v2-13B
|
53 |
-
- PygmalionAI/pygmalion-2-13b
|
54 |
-
- Undi95/StoryTelling
|
55 |
-
- TokenBender/sakhi_13B_roleplayer_NSFW_chat_adapter
|
56 |
-
- nRuaif/Kimiko-v2-13B
|
57 |
-
- The-Face-Of-Goonery/Huginn-13b-FP16
|
58 |
-
- lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
|
59 |
-
- Xwin-LM/Xwin-LM-13B-V0.2
|
60 |
-
|
61 |
-
<!-- description end -->
|
62 |
-
<!-- prompt-template start -->
|
63 |
-
## Prompt template: Alpaca
|
64 |
-
|
65 |
-
```
|
66 |
-
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
67 |
-
|
68 |
-
### Instruction:
|
69 |
-
{prompt}
|
70 |
-
|
71 |
-
### Response:
|
72 |
-
|
73 |
-
```
|
74 |
-
## The secret sauce
|
75 |
-
|
76 |
-
```
|
77 |
-
slices:
|
78 |
-
- sources:
|
79 |
-
- model: Xwin-LM/Xwin-LM-13B-V0.2
|
80 |
-
layer_range: [0, 40]
|
81 |
-
- model: Undi95/MLewd-v2.4-13B
|
82 |
-
layer_range: [0, 40]
|
83 |
-
merge_method: slerp
|
84 |
-
base_model: Xwin-LM/Xwin-LM-13B-V0.2
|
85 |
-
parameters:
|
86 |
-
t:
|
87 |
-
- filter: lm_head
|
88 |
-
value: [0.55]
|
89 |
-
- filter: embed_tokens
|
90 |
-
value: [0.7]
|
91 |
-
- filter: self_attn
|
92 |
-
value: [0.65, 0.35]
|
93 |
-
- filter: mlp
|
94 |
-
value: [0.35, 0.65]
|
95 |
-
- filter: layernorm
|
96 |
-
value: [0.4, 0.6]
|
97 |
-
- filter: modelnorm
|
98 |
-
value: [0.6]
|
99 |
-
- value: 0.5 # fallback for rest of tensors
|
100 |
-
dtype: float16
|
101 |
-
```
|
102 |
-
|
103 |
-
Special thanks to Sushi and Shena ♥
|
104 |
-
|
105 |
-
If you want to support me, you can [here](https://ko-fi.com/undiai).
|
|
|
24 |
|
25 |
### Response:
|
26 |
|
27 |
+
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|