Hugging Face's logo

RichardErkhov
/
Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
RichardErkhov commited on
Commit
510b36e
•
1 Parent(s): 8189d65

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +176 -0
README.md ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ Umbra-v3-MoE-4x11b-2ex - GGUF
11
+ - Model creator: https://huggingface.co/Steelskull/
12
+ - Original model: https://huggingface.co/Steelskull/Umbra-v3-MoE-4x11b-2ex/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Umbra-v3-MoE-4x11b-2ex.Q2_K.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q2_K.gguf) | Q2_K | 12.28GB |
18
+ | [Umbra-v3-MoE-4x11b-2ex.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.IQ3_XS.gguf) | IQ3_XS | 13.74GB |
19
+ | [Umbra-v3-MoE-4x11b-2ex.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.IQ3_S.gguf) | IQ3_S | 14.52GB |
20
+ | [Umbra-v3-MoE-4x11b-2ex.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q3_K_S.gguf) | Q3_K_S | 14.5GB |
21
+ | [Umbra-v3-MoE-4x11b-2ex.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.IQ3_M.gguf) | IQ3_M | 14.8GB |
22
+ | [Umbra-v3-MoE-4x11b-2ex.Q3_K.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q3_K.gguf) | Q3_K | 16.1GB |
23
+ | [Umbra-v3-MoE-4x11b-2ex.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q3_K_M.gguf) | Q3_K_M | 16.1GB |
24
+ | [Umbra-v3-MoE-4x11b-2ex.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q3_K_L.gguf) | Q3_K_L | 17.45GB |
25
+ | [Umbra-v3-MoE-4x11b-2ex.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.IQ4_XS.gguf) | IQ4_XS | 18.13GB |
26
+ | [Umbra-v3-MoE-4x11b-2ex.Q4_0.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q4_0.gguf) | Q4_0 | 18.95GB |
27
+ | [Umbra-v3-MoE-4x11b-2ex.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.IQ4_NL.gguf) | IQ4_NL | 19.13GB |
28
+ | [Umbra-v3-MoE-4x11b-2ex.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q4_K_S.gguf) | Q4_K_S | 19.11GB |
29
+ | [Umbra-v3-MoE-4x11b-2ex.Q4_K.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q4_K.gguf) | Q4_K | 20.32GB |
30
+ | [Umbra-v3-MoE-4x11b-2ex.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q4_K_M.gguf) | Q4_K_M | 20.32GB |
31
+ | [Umbra-v3-MoE-4x11b-2ex.Q4_1.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q4_1.gguf) | Q4_1 | 21.04GB |
32
+ | [Umbra-v3-MoE-4x11b-2ex.Q5_0.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q5_0.gguf) | Q5_0 | 23.13GB |
33
+ | [Umbra-v3-MoE-4x11b-2ex.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q5_K_S.gguf) | Q5_K_S | 23.13GB |
34
+ | [Umbra-v3-MoE-4x11b-2ex.Q5_K.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q5_K.gguf) | Q5_K | 23.84GB |
35
+ | [Umbra-v3-MoE-4x11b-2ex.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q5_K_M.gguf) | Q5_K_M | 23.84GB |
36
+ | [Umbra-v3-MoE-4x11b-2ex.Q5_1.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q5_1.gguf) | Q5_1 | 25.23GB |
37
+ | [Umbra-v3-MoE-4x11b-2ex.Q6_K.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q6_K.gguf) | Q6_K | 27.58GB |
38
+ | [Umbra-v3-MoE-4x11b-2ex.Q8_0.gguf](https://huggingface.co/RichardErkhov/Steelskull_-_Umbra-v3-MoE-4x11b-2ex-gguf/blob/main/Umbra-v3-MoE-4x11b-2ex.Q8_0.gguf) | Q8_0 | 35.72GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ license: apache-2.0
46
+ tags:
47
+ - moe
48
+ - frankenmoe
49
+ - merge
50
+ - mergekit
51
+ - Himitsui/Kaiju-11B
52
+ - Sao10K/Fimbulvetr-11B-v2
53
+ - decapoda-research/Antares-11b-v2
54
+ - beberik/Nyxene-v3-11B
55
+ base_model:
56
+ - Himitsui/Kaiju-11B
57
+ - Sao10K/Fimbulvetr-11B-v2
58
+ - decapoda-research/Antares-11b-v2
59
+ - beberik/Nyxene-v3-11B
60
+ ---
61
+ <!DOCTYPE html>
62
+ <style>
63
+ body {
64
+ font-family: 'Quicksand', sans-serif;
65
+ background: linear-gradient(135deg, #2E3440 0%, #1A202C 100%);
66
+ color: #D8DEE9;
67
+ margin: 0;
68
+ padding: 0;
69
+ font-size: 16px;
70
+ }
71
+
72
+ .container {
73
+ width: 80%;
74
+ max-width: 800px;
75
+ margin: 20px auto;
76
+ background-color: rgba(255, 255, 255, 0.02);
77
+ padding: 20px;
78
+ border-radius: 12px;
79
+ box-shadow: 0 4px 10px rgba(0, 0, 0, 0.2);
80
+ backdrop-filter: blur(10px);
81
+ border: 1px solid rgba(255, 255, 255, 0.1);
82
+ }
83
+
84
+ .header h1 {
85
+ font-size: 28px;
86
+ color: #ECEFF4;
87
+ margin: 0 0 20px 0;
88
+ text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.3);
89
+ }
90
+
91
+ .update-section {
92
+ margin-top: 30px;
93
+ }
94
+
95
+ .update-section h2 {
96
+ font-size: 24px;
97
+ color: #88C0D0;
98
+ }
99
+
100
+ .update-section p {
101
+ font-size: 16px;
102
+ line-height: 1.6;
103
+ color: #ECEFF4;
104
+ }
105
+
106
+ .info img {
107
+ width: 100%;
108
+ border-radius: 10px;
109
+ margin-bottom: 15px;
110
+ }
111
+
112
+ a {
113
+ color: #88C0D0;
114
+ text-decoration: none;
115
+ }
116
+
117
+ a:hover {
118
+ color: #A3BE8C;
119
+ }
120
+
121
+ .button {
122
+ display: inline-block;
123
+ background-color: #5E81AC;
124
+ color: #E5E9F0;
125
+ padding: 10px 20px;
126
+ border-radius: 5px;
127
+ cursor: pointer;
128
+ text-decoration: none;
129
+ }
130
+
131
+ .button:hover {
132
+ background-color: #81A1C1;
133
+ }
134
+
135
+ </style>
136
+ <html lang="en">
137
+ <head>
138
+ <meta charset="UTF-8">
139
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
140
+ <title>Umbra-v3-MoE-4x11b Data Card</title>
141
+ <link href="https://fonts.googleapis.com/css2?family=Quicksand:wght@400;500;600&display=swap" rel="stylesheet">
142
+ </head>
143
+ <body>
144
+ <div class="container">
145
+ <div class="header">
146
+ <h1>Umbra-v3-MoE-4x11b-2ex</h1>
147
+ </div>
148
+ <div class="info">
149
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/MHmVGOLGh4I5MfQ83iiXS.jpeg">
150
+ <p><strong>Creator:</strong> <a href="https://huggingface.co/Steelskull" target="_blank">SteelSkull</a></p>
151
+ <p><strong>About Umbra-v3-MoE-4x11b:</strong> A Mixture of Experts model designed for general assistance with a special knack for storytelling and RP/ERP</p>
152
+ <p>Integrates models from notable sources for enhanced performance in diverse tasks. this is the two expert version</p>
153
+ <p><strong>Source Models:</strong></p>
154
+ <ul>
155
+ <li><a href="https://huggingface.co/Himitsui/Kaiju-11B">Himitsui/Kaiju-11B</a></li>
156
+ <li><a href="https://huggingface.co/Sao10K/Fimbulvetr-11B-v2">Sao10K/Fimbulvetr-11B-v2</a></li>
157
+ <li><a href="https://huggingface.co/decapoda-research/Antares-11b-v2">decapoda-research/Antares-11b-v2</a></li>
158
+ <li><a href="https://huggingface.co/beberik/Nyxene-v3-11B">beberik/Nyxene-v3-11B</a></li>
159
+ </ul>
160
+ </div>
161
+ <div class="update-section">
162
+ <h2>Update-Log:</h2>
163
+ <p>The [Umbra Series] keeps rolling out from the [Lumosia Series] garage, aiming to be your digital Alfred with a side of Shakespeare for those RP/ERP nights.</p>
164
+ <p><strong>What's Fresh in v3?</strong></p>
165
+ <p>Didn’t reinvent the wheel, just slapped on some fancier rims. Upgraded the models and tweaked the prompts a bit. Now, Umbra's not just a general use LLM; it's also focused on spinning stories and "Stories".</p>
166
+ <p><strong>Negative Prompt Minimalism</strong></p>
167
+ <p>Got the prompts to do a bit of a diet and gym routine—more beef on the positives, trimming down the negatives as usual with a dash of my midnight musings.</p>
168
+ <p><strong>Still Guessing, Aren’t We?</strong></p>
169
+ <p>Just so we're clear, "v3" is not the messiah of updates. It’s another experiment in the saga.</p>
170
+ <p>Dive into Umbra v3 and toss your two cents my way. Your feedback is the caffeine in my code marathon.</p>
171
+ </div>
172
+ </div>
173
+ </body>
174
+ </html>
175
+
176
+