Steelskull commited on
Commit
5634035
1 Parent(s): faa7d67

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +123 -14
README.md CHANGED
@@ -10,32 +10,141 @@ tags:
10
 
11
  ---
12
 
13
- ![image/webp]()
14
 
15
- # merge
 
 
 
 
 
 
 
16
 
17
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
 
 
 
 
 
 
 
 
 
18
 
19
- ## Merge Details
20
- ### Merge Method
 
 
 
 
21
 
22
- This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [unsloth/Llama-3.3-70B-Instruct](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct) as a base.
 
 
23
 
24
- ### Models Merged
 
 
 
25
 
26
- The following models were included in the merge:
27
- * [EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0](https://huggingface.co/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0)
28
- * [Sao10K/L3.3-70B-Euryale-v2.3](https://huggingface.co/Sao10K/L3.3-70B-Euryale-v2.3)
 
 
29
 
30
- ### Configuration
 
 
 
 
31
 
32
- The following YAML configuration was used to produce this model:
 
 
 
33
 
34
- ```yaml
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  base_model: unsloth/Llama-3.3-70B-Instruct
36
  merge_method: model_stock
37
  dtype: bfloat16
38
  models:
39
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0
40
  - model: Sao10K/L3.3-70B-Euryale-v2.3
41
- ```
 
 
 
 
 
 
 
 
 
 
 
 
10
 
11
  ---
12
 
13
+ <style>
14
 
15
+ body {
16
+ font-family: 'Quicksand', sans-serif;
17
+ background: linear-gradient(135deg, #2E3440 0%, #1A202C 100%);
18
+ color: #D8DEE9;
19
+ margin: 0;
20
+ padding: 0;
21
+ font-size: 16px;
22
+ }
23
 
24
+ .container {
25
+ width: 80% auto;
26
+ max-width: 1080px auto;
27
+ margin: 20px auto;
28
+ background-color: rgba(255, 255, 255, 0.02);
29
+ padding: 20px;
30
+ border-radius: 12px;
31
+ box-shadow: 0 4px 10px rgba(0, 0, 0, 0.2);
32
+ backdrop-filter: blur(10px);
33
+ border: 1px solid rgba(255, 255, 255, 0.1);
34
+ }
35
 
36
+ .header h1 {
37
+ font-size: 28px;
38
+ color: #ECEFF4;
39
+ margin: 0 0 20px 0;
40
+ text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.3);
41
+ }
42
 
43
+ .update-section {
44
+ margin-top: 30px;
45
+ }
46
 
47
+ .update-section h2 {
48
+ font-size: 24px;
49
+ color: #88C0D0;
50
+ }
51
 
52
+ .update-section p {
53
+ font-size: 16px;
54
+ line-height: 1.6;
55
+ color: #ECEFF4;
56
+ }
57
 
58
+ .info img {
59
+ width: 100%;
60
+ border-radius: 10px;
61
+ margin-bottom: 15px;
62
+ }
63
 
64
+ a {
65
+ color: #88C0D0;
66
+ text-decoration: none;
67
+ }
68
 
69
+ a:hover {
70
+ color: #A3BE8C;
71
+ }
72
+
73
+ .button {
74
+ display: inline-block;
75
+ background-color: #5E81AC;
76
+ color: #E5E9F0;
77
+ padding: 10px 20px;
78
+ border-radius: 5px;
79
+ cursor: pointer;
80
+ text-decoration: none;
81
+ }
82
+
83
+ .button:hover {
84
+ background-color: #81A1C1;
85
+ }
86
+
87
+ pre {
88
+ background-color: #2E3440;
89
+ padding: 10px;
90
+ border-radius: 5px;
91
+ overflow-x: auto;
92
+ }
93
+
94
+ code {
95
+ font-family: 'Courier New', monospace;
96
+ color: #D8DEE9;
97
+ }
98
+
99
+ </style>
100
+ <html lang="en">
101
+ <head>
102
+ <meta charset="UTF-8">
103
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
104
+ <title>L3.3-MS-Evayale-70B</title>
105
+ <link href="https://fonts.googleapis.com/css2?family=Quicksand:wght@400;500;600&display=swap" rel="stylesheet">
106
+ </head>
107
+ <body>
108
+ <div class="container">
109
+ <div class="header">
110
+ <h1>L3.3-MS-Evayale-70B</h1>
111
+ </div>
112
+ <div class="info">
113
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/HFCaVzRpiE05Y46p41qRy.webp">
114
+ <p></p>
115
+ <p><strong>Creator:</strong> <a href="https://huggingface.co/Steelskull" target="_blank">SteelSkull</a></p>
116
+ <h1>About Evayale-70B:</h1>
117
+ <pre><code>Name Legend:
118
+ L3.3 = Llama 3.3
119
+ MS = Model Stock
120
+ Evayale = mix of EVA-LLAMA-0.0 and EURYALE-v2.3
121
+ 70B = its 70B
122
+ </code></pre>
123
+ <p>This model was a created as I liked the storytelling of EVA but the prose and details of scenes of EURYALE, my goal is to merge the robust storytelling of both models while attempting to maintain the positives of both models.</p>
124
+ <h2>My recommended Templates / System prompts: (List of Prompt-Gremlins)</h2>
125
+ <P><a href="https://huggingface.co/Steelskull/L3.3-MS-Evayale-70B/blob/main/LLAMA3.3Settings.json" target="_blank"> LLAMA-3.3-Konnect-Mix </a> <<< Template / System prompt [Made by @.konnect]</P>
126
+ <p><a href="https://huggingface.co/Steelskull/L3.3-MS-Evayale-70B/blob/main/DWK-SP0.02.json" target="_blank"> DWK-SP0.02 </a> <<< System prompt [Made by @daimonwk]</P>
127
+ <h2>Quants: (List of badasses) [will add once created]</h2>
128
+ <p>GGUF Quant: </p>
129
+ <!-- <p> - bartowski: <a href="https://huggingface.co/bartowski/Q2.5-MS-Mistoria-72b-v2-GGUF" target="_blank"> Combined-GGUF </a></p> -->
130
+ <!-- <p> - mradermacher: <a href="https://huggingface.co/mradermacher/Q2.5-MS-Mistoria-72b-v2-GGUF" target="_blank"> GGUF </a>// <a href="https://huggingface.co/mradermacher/Q2.5-MS-Mistoria-72b-v2-i1-GGUF" target="_blank"> Imat-GGUF </a></p> -->
131
+ <h3>Config:</h3>
132
+ <pre><code>MODEL_NAME = "L3.3-MS-Evayale-70B"
133
  base_model: unsloth/Llama-3.3-70B-Instruct
134
  merge_method: model_stock
135
  dtype: bfloat16
136
  models:
137
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0
138
  - model: Sao10K/L3.3-70B-Euryale-v2.3
139
+ </code></pre>
140
+ <p><strong>If you wish to support:</strong></p>
141
+ </div>
142
+ <div class="donation-section">
143
+ <a href="https://ko-fi.com/Y8Y0AO2XE" target="_blank">
144
+ <img height="36" style="border:0px;height:36px;" src="https://storage.ko-fi.com/cdn/kofi2.png?v=3" border="0" alt="Buy Me a Coffee at ko-fi.com" />
145
+ </a>
146
+ </div>
147
+ </div>
148
+ </div>
149
+ </body>
150
+ </html>