Steelskull commited on
Commit
b7f8cbb
1 Parent(s): 8b287a1

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +124 -0
README.md ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!DOCTYPE html>
2
+ <html lang="en">
3
+ <head>
4
+ <meta charset="UTF-8">
5
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
6
+ <title>G2-MS-Nyxora-27b Data Card</title>
7
+ <link href="https://fonts.googleapis.com/css2?family=Quicksand:wght@400;500;600&display=swap" rel="stylesheet">
8
+ <style>
9
+ body, html {
10
+ height: 100%;
11
+ margin: 0;
12
+ padding: 0;
13
+ font-family: 'Quicksand', sans-serif;
14
+ background: linear-gradient(135deg, #0a1128 0%, #1c2541 100%);
15
+ color: #e0e1dd;
16
+ font-size: 16px;
17
+ }
18
+ .container {
19
+ width: 100%;
20
+ height: 100%;
21
+ padding: 20px;
22
+ margin: 0;
23
+ background-color: rgba(255, 255, 255, 0.05);
24
+ border-radius: 12px;
25
+ box-shadow: 0 4px 10px rgba(0, 0, 0, 0.3);
26
+ backdrop-filter: blur(10px);
27
+ border: 1px solid rgba(255, 255, 255, 0.1);
28
+ }
29
+ .header h1 {
30
+ font-size: 28px;
31
+ color: #4cc9f0;
32
+ margin: 0 0 20px 0;
33
+ text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.3);
34
+ }
35
+ .update-section h2 {
36
+ font-size: 24px;
37
+ color: #7209b7;
38
+ }
39
+ .update-section p {
40
+ font-size: 16px;
41
+ line-height: 1.6;
42
+ color: #e0e1dd;
43
+ }
44
+ .info img {
45
+ width: 100%;
46
+ border-radius: 10px;
47
+ margin-bottom: 15px;
48
+ }
49
+ a {
50
+ color: #4cc9f0;
51
+ text-decoration: none;
52
+ }
53
+ a:hover {
54
+ color: #f72585;
55
+ }
56
+ .button {
57
+ display: inline-block;
58
+ background-color: #3a0ca3;
59
+ color: #e0e1dd;
60
+ padding: 10px 20px;
61
+ border-radius: 5px;
62
+ cursor: pointer;
63
+ text-decoration: none;
64
+ }
65
+ .button:hover {
66
+ background-color: #7209b7;
67
+ }
68
+ pre {
69
+ background-color: #1c2541;
70
+ padding: 10px;
71
+ border-radius: 5px;
72
+ overflow-x: auto;
73
+ }
74
+ code {
75
+ font-family: 'Courier New', monospace;
76
+ color: #e0e1dd;
77
+ }
78
+ </style>
79
+ </head>
80
+ <body>
81
+ <div class="container">
82
+ <div class="header">
83
+ <h1>G2-MS-Nyxora-27b</h1>
84
+ </div>
85
+ <div class="info">
86
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/rqcAEjzvLpQwu2Cg3g1hH.png" alt="Model Image">
87
+ <p>Now that the cute anime girl has your attention.</p>
88
+ <p><strong>Creator:</strong> <a href="https://huggingface.co/Steelskull" target="_blank">SteelSkull</a></p>
89
+ <h1>About G2-MS-Nyxora-27b:</h1>
90
+ <pre><code><strong>Model Name Legend =</strong>
91
+ "G2 = Gemma 2"
92
+ "MS = Model_stock"</code></pre>
93
+ <p>This model represents an experimental foray into 27b models. Feedback is welcome for further improvements.</p>
94
+ <p>G2-MS-Nyxora-27b combines multiple models' strengths to provide a versatile assistant for various tasks, including general use, storytelling, roleplay, and mature content.</p>
95
+ <p>The Model_stock merge method ensures the model remains focused, tailored, and high-quality.</p>
96
+ <h2>Quants:</h2>
97
+ <p>Will add once found</p>
98
+ <h3>Config:</h3>
99
+ <pre><code>MODEL_NAME = "G2-MS-Nyxora-27b"
100
+ yaml_config = """
101
+ base_model: google/gemma-2-27b-it
102
+ merge_method: model_stock
103
+ dtype: bfloat16
104
+ models:
105
+ - model: TheDrummer/Big-Tiger-Gemma-27B-v1
106
+ - model: migtissera/Tess-v2.5-Gemma-2-27B-alpha
107
+ """
108
+ </code></pre>
109
+ <h4>Source Model Details:</h4>
110
+ <p><strong>TheDrummer/Big-Tiger-Gemma-27B-v1:</strong><br>
111
+ A decensored version of the Gemma 27B model.
112
+ </p>
113
+ <p><strong>migtissera/Tess-v2.5-Gemma-2-27B-alpha:</strong><br>
114
+ The latest state-of-the-art model in the Tess series, Tess-v2.5.2, offers significant improvements in reasoning, coding, and mathematics. It ranks #1 on the MMLU benchmark among open weight models and outperforms several frontier closed models.
115
+ </p>
116
+ <p><strong>Gemma-2-27b-it:</strong><br>
117
+ A lightweight, state-of-the-art model from Google, well-suited for various text generation tasks. Its small size allows deployment in resource-limited environments, fostering AI innovation for all.
118
+ </p>
119
+ <h4>Merge Method Details:</h4>
120
+ <p>Model_stock Uses some neat geometric properties of fine tuned models to compute good weights for linear interpolation.</p>
121
+ </div>
122
+ </div>
123
+ </body>
124
+ </html>