Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,324 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- fine-tuning
|
| 5 |
+
- prose
|
| 6 |
+
- KTO
|
| 7 |
+
- axolotl
|
| 8 |
+
- finetune
|
| 9 |
+
- roleplaying
|
| 10 |
+
- creative-writing
|
| 11 |
+
---
|
| 12 |
+
<style>
|
| 13 |
+
@import url('https://fonts.googleapis.com/css2?family=Share+Tech+Mono&display=swap');
|
| 14 |
+
|
| 15 |
+
body {
|
| 16 |
+
font-family: 'Share Tech Mono', monospace;
|
| 17 |
+
background: #121212;
|
| 18 |
+
color: #E0E0E0;
|
| 19 |
+
margin: 0;
|
| 20 |
+
padding: 0;
|
| 21 |
+
font-size: 16px;
|
| 22 |
+
}
|
| 23 |
+
.container {
|
| 24 |
+
margin: 20px auto;
|
| 25 |
+
background-color: #1E1E1E;
|
| 26 |
+
padding: 20px;
|
| 27 |
+
border-radius: 8px;
|
| 28 |
+
box-shadow: 0 0 25px rgba(255, 0, 51, 0.3);
|
| 29 |
+
border: 1px solid #FF0033;
|
| 30 |
+
position: relative;
|
| 31 |
+
max-width: 1000px;
|
| 32 |
+
}
|
| 33 |
+
.header h1 {
|
| 34 |
+
font-size: 32px;
|
| 35 |
+
color: #FF0033;
|
| 36 |
+
margin: 0 0 20px 0;
|
| 37 |
+
text-align: center;
|
| 38 |
+
text-shadow: 0 0 10px rgba(255, 0, 51, 0.7);
|
| 39 |
+
text-transform: uppercase;
|
| 40 |
+
}
|
| 41 |
+
.section {
|
| 42 |
+
margin-top: 30px;
|
| 43 |
+
}
|
| 44 |
+
.section h2 {
|
| 45 |
+
font-size: 26px;
|
| 46 |
+
color: #FF0033;
|
| 47 |
+
text-align: center;
|
| 48 |
+
border-bottom: 1px solid #FF0033;
|
| 49 |
+
padding-bottom: 10px;
|
| 50 |
+
margin-bottom: 20px;
|
| 51 |
+
}
|
| 52 |
+
.info p {
|
| 53 |
+
color: #E0E0E0;
|
| 54 |
+
line-height: 1.7;
|
| 55 |
+
font-size: 16px;
|
| 56 |
+
}
|
| 57 |
+
.info img {
|
| 58 |
+
width: 100%;
|
| 59 |
+
max-width: 600px;
|
| 60 |
+
border-radius: 4px;
|
| 61 |
+
margin: 0 auto 15px;
|
| 62 |
+
display: block;
|
| 63 |
+
box-shadow: 0 0 20px rgba(0, 0, 0, 0.5);
|
| 64 |
+
border: 1px solid #444;
|
| 65 |
+
}
|
| 66 |
+
a {
|
| 67 |
+
color: #FF0033;
|
| 68 |
+
text-decoration: none;
|
| 69 |
+
transition: color 0.2s ease, text-shadow 0.2s ease;
|
| 70 |
+
}
|
| 71 |
+
a:hover {
|
| 72 |
+
color: #FFFFFF;
|
| 73 |
+
text-shadow: 0 0 8px rgba(255, 0, 51, 0.8);
|
| 74 |
+
}
|
| 75 |
+
.button {
|
| 76 |
+
display: inline-block;
|
| 77 |
+
background-color: transparent;
|
| 78 |
+
color: #FF0033;
|
| 79 |
+
padding: 10px 20px;
|
| 80 |
+
border-radius: 4px;
|
| 81 |
+
cursor: pointer;
|
| 82 |
+
text-decoration: none;
|
| 83 |
+
border: 1px solid #FF0033;
|
| 84 |
+
transition: background-color 0.2s ease, box-shadow 0.2s ease, color 0.2s ease;
|
| 85 |
+
}
|
| 86 |
+
.button:hover {
|
| 87 |
+
background-color: #FF0033;
|
| 88 |
+
color: #121212;
|
| 89 |
+
box-shadow: 0 0 15px rgba(255, 0, 51, 0.7);
|
| 90 |
+
}
|
| 91 |
+
pre {
|
| 92 |
+
background-color: #0d0d0d;
|
| 93 |
+
padding: 15px;
|
| 94 |
+
border-radius: 4px;
|
| 95 |
+
overflow-x: auto;
|
| 96 |
+
border: 1px solid #444;
|
| 97 |
+
border-left: 3px solid #FF0033;
|
| 98 |
+
color: #E0E0E0;
|
| 99 |
+
}
|
| 100 |
+
code {
|
| 101 |
+
font-family: 'Share Tech Mono', monospace;
|
| 102 |
+
color: #E0E0E0;
|
| 103 |
+
}
|
| 104 |
+
.info-card {
|
| 105 |
+
background: #2a2a2a;
|
| 106 |
+
border: 1px solid #444;
|
| 107 |
+
border-radius: 8px;
|
| 108 |
+
overflow: hidden;
|
| 109 |
+
}
|
| 110 |
+
.info-header {
|
| 111 |
+
background: #1a1a1a;
|
| 112 |
+
padding: 20px;
|
| 113 |
+
border-bottom: 1px solid #444;
|
| 114 |
+
}
|
| 115 |
+
.info-header h3 {
|
| 116 |
+
color: #FFFFFF;
|
| 117 |
+
margin: 0 0 10px 0;
|
| 118 |
+
font-size: 22px;
|
| 119 |
+
text-align: center;
|
| 120 |
+
}
|
| 121 |
+
.model-tags {
|
| 122 |
+
display: flex;
|
| 123 |
+
justify-content: center;
|
| 124 |
+
gap: 10px;
|
| 125 |
+
flex-wrap: wrap;
|
| 126 |
+
}
|
| 127 |
+
.model-tag {
|
| 128 |
+
background: #121212;
|
| 129 |
+
color: #FF0033;
|
| 130 |
+
padding: 5px 10px;
|
| 131 |
+
border-radius: 4px;
|
| 132 |
+
font-size: 12px;
|
| 133 |
+
border: 1px solid #FF0033;
|
| 134 |
+
text-transform: uppercase;
|
| 135 |
+
}
|
| 136 |
+
.model-composition {
|
| 137 |
+
padding: 20px;
|
| 138 |
+
border-bottom: 1px solid #444;
|
| 139 |
+
}
|
| 140 |
+
.model-composition h4 {
|
| 141 |
+
color: #FFFFFF;
|
| 142 |
+
margin: 0 0 15px 0;
|
| 143 |
+
font-size: 18px;
|
| 144 |
+
text-align: center;
|
| 145 |
+
}
|
| 146 |
+
.composition-list {
|
| 147 |
+
list-style: none;
|
| 148 |
+
padding: 0;
|
| 149 |
+
margin: 0;
|
| 150 |
+
display: grid;
|
| 151 |
+
gap: 10px;
|
| 152 |
+
}
|
| 153 |
+
.composition-list li {
|
| 154 |
+
color: #E0E0E0;
|
| 155 |
+
display: flex;
|
| 156 |
+
align-items: baseline;
|
| 157 |
+
gap: 8px;
|
| 158 |
+
}
|
| 159 |
+
.model-component {
|
| 160 |
+
font-weight: bold;
|
| 161 |
+
min-width: 120px;
|
| 162 |
+
}
|
| 163 |
+
.model-description {
|
| 164 |
+
padding: 20px;
|
| 165 |
+
background: #2a2a2a;
|
| 166 |
+
}
|
| 167 |
+
.metrics-section {
|
| 168 |
+
margin-bottom: 30px;
|
| 169 |
+
}
|
| 170 |
+
.metrics-section details {
|
| 171 |
+
background: #2a2a2a;
|
| 172 |
+
border: 1px solid #444;
|
| 173 |
+
border-radius: 8px;
|
| 174 |
+
padding: 15px;
|
| 175 |
+
margin-bottom: 15px;
|
| 176 |
+
}
|
| 177 |
+
.metrics-section summary {
|
| 178 |
+
color: #FF0033;
|
| 179 |
+
font-size: 18px;
|
| 180 |
+
cursor: pointer;
|
| 181 |
+
outline: none;
|
| 182 |
+
padding: 5px 0;
|
| 183 |
+
text-align: center;
|
| 184 |
+
font-weight: bold;
|
| 185 |
+
}
|
| 186 |
+
.creator-section {
|
| 187 |
+
margin: 20px 0;
|
| 188 |
+
}
|
| 189 |
+
.creator-badge {
|
| 190 |
+
display: inline-flex;
|
| 191 |
+
align-items: center;
|
| 192 |
+
background: #1a1a1a;
|
| 193 |
+
border: 1px solid #444;
|
| 194 |
+
border-radius: 4px;
|
| 195 |
+
padding: 10px 15px;
|
| 196 |
+
}
|
| 197 |
+
.creator-label {
|
| 198 |
+
color: #E0E0E0;
|
| 199 |
+
font-size: 14px;
|
| 200 |
+
margin-right: 8px;
|
| 201 |
+
}
|
| 202 |
+
.creator-link {
|
| 203 |
+
display: flex;
|
| 204 |
+
align-items: center;
|
| 205 |
+
gap: 5px;
|
| 206 |
+
color: #FF0033;
|
| 207 |
+
text-decoration: none;
|
| 208 |
+
transition: all 0.2s ease;
|
| 209 |
+
}
|
| 210 |
+
.creator-name {
|
| 211 |
+
font-weight: 600;
|
| 212 |
+
}
|
| 213 |
+
.creator-arrow {
|
| 214 |
+
font-size: 16px;
|
| 215 |
+
transition: transform 0.2s ease;
|
| 216 |
+
}
|
| 217 |
+
.creator-link:hover .creator-arrow {
|
| 218 |
+
transform: translateX(5px);
|
| 219 |
+
}
|
| 220 |
+
.link-arrow {
|
| 221 |
+
display: inline-block;
|
| 222 |
+
transition: transform 0.2s ease;
|
| 223 |
+
}
|
| 224 |
+
a:hover .link-arrow {
|
| 225 |
+
transform: translateX(5px);
|
| 226 |
+
}
|
| 227 |
+
.axolotl-container {
|
| 228 |
+
text-align: center;
|
| 229 |
+
margin: 30px 0;
|
| 230 |
+
filter: invert(1) hue-rotate(180deg);
|
| 231 |
+
}
|
| 232 |
+
.axolotl-container img {
|
| 233 |
+
max-width: 300px;
|
| 234 |
+
border-radius: 8px;
|
| 235 |
+
box-shadow: 0 2px 10px rgba(0, 0, 0, 0.3);
|
| 236 |
+
border: 1px solid #000000;
|
| 237 |
+
}
|
| 238 |
+
</style>
|
| 239 |
+
<html lang="en">
|
| 240 |
+
<head>
|
| 241 |
+
<meta charset="UTF-8">
|
| 242 |
+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
| 243 |
+
<title>Rei-KTO-24B</title>
|
| 244 |
+
</head>
|
| 245 |
+
<body>
|
| 246 |
+
<div class="container">
|
| 247 |
+
<div class="header">
|
| 248 |
+
<h1>Rei-KTO-24B</h1>
|
| 249 |
+
</div>
|
| 250 |
+
<div class="info">
|
| 251 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/qUdM9qgZWeyfxwdds9QRZ.jpeg" alt="Model banner">
|
| 252 |
+
<div style="text-align: center;">
|
| 253 |
+
<div class="creator-section">
|
| 254 |
+
<div class="creator-badge">
|
| 255 |
+
<span class="creator-label">Created by</span>
|
| 256 |
+
<a href="https://huggingface.co/Delta-Vector" target="_blank" class="creator-link">
|
| 257 |
+
<span class="creator-name">Delta-Vector</span>
|
| 258 |
+
<span class="creator-arrow">→</span>
|
| 259 |
+
</a>
|
| 260 |
+
</div>
|
| 261 |
+
</div>
|
| 262 |
+
<div class="model-info">
|
| 263 |
+
<h2>Model Information</h2>
|
| 264 |
+
<div class="info-card">
|
| 265 |
+
<div class="info-header">
|
| 266 |
+
<h>Rei-KTO-24B</h3>
|
| 267 |
+
<div class="model-tags">
|
| 268 |
+
<span class="model-tag">KTO enhanced</span>
|
| 269 |
+
<span class="model-tag">Painted Fantasy Finetune</span>
|
| 270 |
+
<span class="model-tag">Creative Prose</span>
|
| 271 |
+
</div>
|
| 272 |
+
</div>
|
| 273 |
+
<div class="model-description">
|
| 274 |
+
<p>A model meant to replicate the style and prose of the Anthropic Claude models, Opus and Sonnet. This model is meant for Roleplaying/Creative-writing, Has some nice smarts without being too sloppy, etc - It's pretty good. Trained in 2 steps, Firstly SFT trained on Zerofata's PaintedFantasy which i found great at anime-otaku-esque characters, and then KTO'd to improve coherency and Instruct Following </p>
|
| 275 |
+
</div>
|
| 276 |
+
</div>
|
| 277 |
+
</div>
|
| 278 |
+
<div class="section">
|
| 279 |
+
<h2>Quantized Versions</h2>
|
| 280 |
+
<div class="info-card">
|
| 281 |
+
<div class="model-composition">
|
| 282 |
+
<h4>Available Downloads</h4>
|
| 283 |
+
<ul class="composition-list">
|
| 284 |
+
<li><span class="model-component"><a href="" target="_blank">GGUF Format</a></span>For use with LLama.cpp & Forks (Coming Soon!)</li>
|
| 285 |
+
<li><span class="model-component"><a href="" target="_blank">EXL2 Format</a></span>For use with TabbyAPI (Coming Soon!)</li>
|
| 286 |
+
</ul>
|
| 287 |
+
</div>
|
| 288 |
+
</div>
|
| 289 |
+
</div>
|
| 290 |
+
<div class="section">
|
| 291 |
+
<h2>Prompting</h2>
|
| 292 |
+
<p>The model is tuned with V7 Tekken formatting. A typical input would look like this:</p>
|
| 293 |
+
<pre><code><span style="color:#FF0033;"><s>[SYSTEM_PROMPT]system_prompt[/SYSTEM_PROMPT][INST]Hi there![/INST]Nice to meet you!</s>[INST]Can I ask a question?[/INST]
|
| 294 |
+
</code></pre>
|
| 295 |
+
</div>
|
| 296 |
+
<div class="section">
|
| 297 |
+
<h2>Training</h2>
|
| 298 |
+
<p>Training was done in 2 steps, SFT>KTO</p>
|
| 299 |
+
<div class="metrics-section">
|
| 300 |
+
<details>
|
| 301 |
+
<summary>Access Configs</summary>
|
| 302 |
+
<pre><code> SFT: https://wandb.ai/new-eden/Painted-Fantasy-Rei/artifacts/axolotl-config/config-u7to9d5q/v0/files/axolotl_config_f0p7vnaf.yml
|
| 303 |
+
KTO : https://wandb.ai/new-eden/Painted-Rei/artifacts/axolotl-config/config-8n37w77c/v0/files/axolotl_config_hvrd2tzn.yml
|
| 304 |
+
</code></pre>
|
| 305 |
+
</details>
|
| 306 |
+
</div>
|
| 307 |
+
</div>
|
| 308 |
+
<div class="section">
|
| 309 |
+
<h2>Training</h2>
|
| 310 |
+
<p>The training was done for 2 epochs using 8 x A100s for 24 hours/p>
|
| 311 |
+
<p style="text-align: center; margin-top: 20px;">
|
| 312 |
+
<div class="axolotl-container">
|
| 313 |
+
<a href="https://github.com/OpenAccess-AI-Collective/axolotl" target="_blank">
|
| 314 |
+
<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl">
|
| 315 |
+
</a>
|
| 316 |
+
</div>
|
| 317 |
+
<div class="section">
|
| 318 |
+
<h2>Credits</h2>
|
| 319 |
+
<p>Thank you to <a href="https://huggingface.co/lucyknada">Lucy Knada</a>, <a href="https://huggingface.co/Ateron">Ateron</a>, <a href="https://huggingface.co/AliCat2">Alicat</a>, <a href="https://huggingface.co/intervitens">Intervitens</a>, <a href="https://huggingface.co/cgato">Cgato</a>, <a href="https://huggingface.co/kubernetes-bad">Kubernetes Bad</a> and the rest of <a href="https://huggingface.co/anthracite-org">Anthracite</a>.</p>
|
| 320 |
+
</div>
|
| 321 |
+
</div>
|
| 322 |
+
</div>
|
| 323 |
+
</body>
|
| 324 |
+
</html>
|