Upload 1.html with huggingface_hub
Browse files
1.html
ADDED
|
@@ -0,0 +1,285 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<!DOCTYPE html>
|
| 2 |
+
<html lang="zh-CN">
|
| 3 |
+
<head>
|
| 4 |
+
<meta charset="UTF-8">
|
| 5 |
+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
| 6 |
+
<title>数据总量概览:预训练与后训练阶段</title>
|
| 7 |
+
<style>
|
| 8 |
+
:root {
|
| 9 |
+
--primary-color: #2563eb;
|
| 10 |
+
--secondary-color: #10b981;
|
| 11 |
+
--text-main: #1f2937;
|
| 12 |
+
--text-muted: #6b7280;
|
| 13 |
+
--bg-color: #ffffff;
|
| 14 |
+
--card-bg: #f9fafb;
|
| 15 |
+
--border-color: #e5e7eb;
|
| 16 |
+
}
|
| 17 |
+
|
| 18 |
+
body {
|
| 19 |
+
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, "Helvetica Neue", Arial, sans-serif;
|
| 20 |
+
background-color: var(--bg-color);
|
| 21 |
+
color: var(--text-main);
|
| 22 |
+
margin: 0;
|
| 23 |
+
padding: 40px 60px;
|
| 24 |
+
box-sizing: border-box;
|
| 25 |
+
display: flex;
|
| 26 |
+
flex-direction: column;
|
| 27 |
+
height: 100vh;
|
| 28 |
+
justify-content: center;
|
| 29 |
+
}
|
| 30 |
+
|
| 31 |
+
h1 {
|
| 32 |
+
text-align: center;
|
| 33 |
+
font-size: 2.5rem;
|
| 34 |
+
margin-bottom: 10px;
|
| 35 |
+
color: #111827;
|
| 36 |
+
font-weight: 800;
|
| 37 |
+
letter-spacing: 2px;
|
| 38 |
+
}
|
| 39 |
+
|
| 40 |
+
.subtitle {
|
| 41 |
+
text-align: center;
|
| 42 |
+
color: var(--text-muted);
|
| 43 |
+
font-size: 1.2rem;
|
| 44 |
+
margin-bottom: 40px;
|
| 45 |
+
}
|
| 46 |
+
|
| 47 |
+
.container {
|
| 48 |
+
display: flex;
|
| 49 |
+
gap: 40px;
|
| 50 |
+
width: 100%;
|
| 51 |
+
max-width: 1400px;
|
| 52 |
+
margin: 0 auto;
|
| 53 |
+
flex: 1;
|
| 54 |
+
}
|
| 55 |
+
|
| 56 |
+
.column {
|
| 57 |
+
flex: 1;
|
| 58 |
+
display: flex;
|
| 59 |
+
flex-direction: column;
|
| 60 |
+
gap: 20px;
|
| 61 |
+
}
|
| 62 |
+
|
| 63 |
+
.column-header {
|
| 64 |
+
font-size: 1.8rem;
|
| 65 |
+
font-weight: bold;
|
| 66 |
+
padding-bottom: 15px;
|
| 67 |
+
border-bottom: 3px solid;
|
| 68 |
+
display: flex;
|
| 69 |
+
align-items: center;
|
| 70 |
+
gap: 10px;
|
| 71 |
+
}
|
| 72 |
+
|
| 73 |
+
.pre-train .column-header {
|
| 74 |
+
color: var(--primary-color);
|
| 75 |
+
border-bottom-color: var(--primary-color);
|
| 76 |
+
}
|
| 77 |
+
|
| 78 |
+
.post-train .column-header {
|
| 79 |
+
color: var(--secondary-color);
|
| 80 |
+
border-bottom-color: var(--secondary-color);
|
| 81 |
+
}
|
| 82 |
+
|
| 83 |
+
.card {
|
| 84 |
+
background-color: var(--card-bg);
|
| 85 |
+
border: 1px solid var(--border-color);
|
| 86 |
+
border-radius: 12px;
|
| 87 |
+
padding: 24px;
|
| 88 |
+
box-shadow: 0 4px 6px -1px rgba(0, 0, 0, 0.05), 0 2px 4px -1px rgba(0, 0, 0, 0.03);
|
| 89 |
+
transition: transform 0.2s ease;
|
| 90 |
+
}
|
| 91 |
+
|
| 92 |
+
.card:hover {
|
| 93 |
+
transform: translateY(-2px);
|
| 94 |
+
box-shadow: 0 10px 15px -3px rgba(0, 0, 0, 0.05), 0 4px 6px -2px rgba(0, 0, 0, 0.025);
|
| 95 |
+
}
|
| 96 |
+
|
| 97 |
+
.card-header {
|
| 98 |
+
display: flex;
|
| 99 |
+
justify-content: space-between;
|
| 100 |
+
align-items: center;
|
| 101 |
+
margin-bottom: 16px;
|
| 102 |
+
}
|
| 103 |
+
|
| 104 |
+
.card-title {
|
| 105 |
+
font-size: 1.4rem;
|
| 106 |
+
font-weight: bold;
|
| 107 |
+
display: flex;
|
| 108 |
+
align-items: center;
|
| 109 |
+
gap: 8px;
|
| 110 |
+
}
|
| 111 |
+
|
| 112 |
+
.card-total {
|
| 113 |
+
font-size: 1.2rem;
|
| 114 |
+
font-weight: 900;
|
| 115 |
+
background: #e0f2fe;
|
| 116 |
+
color: #0369a1;
|
| 117 |
+
padding: 4px 12px;
|
| 118 |
+
border-radius: 20px;
|
| 119 |
+
}
|
| 120 |
+
|
| 121 |
+
.post-train .card-total {
|
| 122 |
+
background: #d1fae5;
|
| 123 |
+
color: #047857;
|
| 124 |
+
}
|
| 125 |
+
|
| 126 |
+
.data-list {
|
| 127 |
+
list-style: none;
|
| 128 |
+
padding: 0;
|
| 129 |
+
margin: 0;
|
| 130 |
+
}
|
| 131 |
+
|
| 132 |
+
.data-list li {
|
| 133 |
+
position: relative;
|
| 134 |
+
padding-left: 20px;
|
| 135 |
+
margin-bottom: 12px;
|
| 136 |
+
line-height: 1.6;
|
| 137 |
+
color: #374151;
|
| 138 |
+
}
|
| 139 |
+
|
| 140 |
+
.data-list li::before {
|
| 141 |
+
content: "•";
|
| 142 |
+
position: absolute;
|
| 143 |
+
left: 0;
|
| 144 |
+
color: #9ca3af;
|
| 145 |
+
font-size: 1.2rem;
|
| 146 |
+
}
|
| 147 |
+
|
| 148 |
+
.highlight {
|
| 149 |
+
font-weight: 600;
|
| 150 |
+
color: #111827;
|
| 151 |
+
}
|
| 152 |
+
|
| 153 |
+
.tag {
|
| 154 |
+
display: inline-block;
|
| 155 |
+
background-color: #f3f4f6;
|
| 156 |
+
border: 1px solid #d1d5db;
|
| 157 |
+
color: #4b5563;
|
| 158 |
+
font-size: 0.85rem;
|
| 159 |
+
padding: 2px 8px;
|
| 160 |
+
border-radius: 4px;
|
| 161 |
+
margin-left: 6px;
|
| 162 |
+
vertical-align: middle;
|
| 163 |
+
}
|
| 164 |
+
|
| 165 |
+
.method-box {
|
| 166 |
+
margin-top: 12px;
|
| 167 |
+
padding: 12px;
|
| 168 |
+
background-color: #f8fafc;
|
| 169 |
+
border-left: 4px solid var(--secondary-color);
|
| 170 |
+
border-radius: 0 8px 8px 0;
|
| 171 |
+
font-size: 0.95rem;
|
| 172 |
+
}
|
| 173 |
+
|
| 174 |
+
.arrow {
|
| 175 |
+
color: #9ca3af;
|
| 176 |
+
margin: 0 6px;
|
| 177 |
+
}
|
| 178 |
+
</style>
|
| 179 |
+
</head>
|
| 180 |
+
<body>
|
| 181 |
+
|
| 182 |
+
<h1>多模态大模型数据大盘</h1>
|
| 183 |
+
<div class="subtitle">Data Volume Overview: Pre-training & Post-training</div>
|
| 184 |
+
|
| 185 |
+
<div class="container">
|
| 186 |
+
<div class="column pre-train">
|
| 187 |
+
<div class="column-header">
|
| 188 |
+
<span>⚡ 预训练阶段 (Pre-training)</span>
|
| 189 |
+
</div>
|
| 190 |
+
|
| 191 |
+
<div class="card">
|
| 192 |
+
<div class="card-header">
|
| 193 |
+
<div class="card-title">🖼️ T2I (Text-to-Image)</div>
|
| 194 |
+
<div class="card-total">~ 812M+</div>
|
| 195 |
+
</div>
|
| 196 |
+
<ul class="data-list">
|
| 197 |
+
<li><span class="highlight">华山落盘数据:800M</span>
|
| 198 |
+
<div style="margin-top: 4px; font-size: 0.95rem; color: var(--text-muted);">
|
| 199 |
+
含 240M Qwen3vl4b 重打标 Dense 数据 <span class="tag">平均387 tokens</span>,其余为短标注
|
| 200 |
+
</div>
|
| 201 |
+
</li>
|
| 202 |
+
<li><span class="highlight">Banana 蒸馏数据:2.2M</span> <span class="tag">Gemini标注</span></li>
|
| 203 |
+
<li><span class="highlight">自收集开源数据:10M</span> <span class="tag">高质量美学图片</span></li>
|
| 204 |
+
</ul>
|
| 205 |
+
</div>
|
| 206 |
+
|
| 207 |
+
<div class="card">
|
| 208 |
+
<div class="card-header">
|
| 209 |
+
<div class="card-title">🎵 T2A (Text-to-Audio)</div>
|
| 210 |
+
<div class="card-total">56,300 Hours+</div>
|
| 211 |
+
</div>
|
| 212 |
+
<ul class="data-list">
|
| 213 |
+
<li><span class="highlight">Audio 数据:6,300 小时</span> (约 2.3M)</li>
|
| 214 |
+
<li><span class="highlight">Speech 数据:50,000 小时</span> (约 33M)</li>
|
| 215 |
+
<li><span class="highlight">自收集开源数据</span> (补充来源)</li>
|
| 216 |
+
</ul>
|
| 217 |
+
</div>
|
| 218 |
+
|
| 219 |
+
<div class="card">
|
| 220 |
+
<div class="card-header">
|
| 221 |
+
<div class="card-title">🎬 T2V (Text-to-Video)</div>
|
| 222 |
+
<div class="card-total">~ 100M+</div>
|
| 223 |
+
</div>
|
| 224 |
+
<div style="margin-bottom: 10px;"><span class="tag">>480p</span> <span class="tag">时长 3~10s</span></div>
|
| 225 |
+
<ul class="data-list">
|
| 226 |
+
<li><span class="highlight">华山数据:100M</span>
|
| 227 |
+
<div style="margin-top: 4px; font-size: 0.95rem; color: var(--text-muted);">
|
| 228 |
+
含 22M 数据经 Gemini 重打标注
|
| 229 |
+
</div>
|
| 230 |
+
</li>
|
| 231 |
+
<li><span class="highlight">Seedance 蒸馏:350K</span></li>
|
| 232 |
+
</ul>
|
| 233 |
+
</div>
|
| 234 |
+
|
| 235 |
+
<div class="card">
|
| 236 |
+
<div class="card-header">
|
| 237 |
+
<div class="card-title">🎞️ T2AV (Text-to-Audio-Video)</div>
|
| 238 |
+
<div class="card-total">2M</div>
|
| 239 |
+
</div>
|
| 240 |
+
</div>
|
| 241 |
+
</div>
|
| 242 |
+
|
| 243 |
+
<div class="column post-train">
|
| 244 |
+
<div class="column-header">
|
| 245 |
+
<span>🎯 后训练阶段 (Post-training)</span>
|
| 246 |
+
</div>
|
| 247 |
+
|
| 248 |
+
<div class="card">
|
| 249 |
+
<div class="card-header">
|
| 250 |
+
<div class="card-title">✨ I2I (Image-to-Image)</div>
|
| 251 |
+
<div class="card-total">5M</div>
|
| 252 |
+
</div>
|
| 253 |
+
<ul class="data-list">
|
| 254 |
+
<li><span class="highlight">Nano Banana 蒸馏数据:5M</span> <span class="tag">1K 分辨率</span></li>
|
| 255 |
+
</ul>
|
| 256 |
+
</div>
|
| 257 |
+
|
| 258 |
+
<div class="card">
|
| 259 |
+
<div class="card-header">
|
| 260 |
+
<div class="card-title">📽️ I2V (Image-to-Video)</div>
|
| 261 |
+
<div class="card-total">5M</div>
|
| 262 |
+
</div>
|
| 263 |
+
<ul class="data-list">
|
| 264 |
+
<li><span class="highlight">精选图生视频数据:5M</span></li>
|
| 265 |
+
</ul>
|
| 266 |
+
</div>
|
| 267 |
+
|
| 268 |
+
<div class="card">
|
| 269 |
+
<div class="card-header">
|
| 270 |
+
<div class="card-title">🎮 交互数据 (Interactive)</div>
|
| 271 |
+
<div class="card-total">1M</div>
|
| 272 |
+
</div>
|
| 273 |
+
<ul class="data-list">
|
| 274 |
+
<li><span class="highlight">游戏交互控制数据:1M</span></li>
|
| 275 |
+
</ul>
|
| 276 |
+
<div class="method-box">
|
| 277 |
+
<strong>🔧 构造链路:</strong><br>
|
| 278 |
+
YouTube游戏视频 <span class="arrow">➔</span> VGGt估计姿态 <span class="arrow">➔</span> 提取控制信号
|
| 279 |
+
</div>
|
| 280 |
+
</div>
|
| 281 |
+
</div>
|
| 282 |
+
</div>
|
| 283 |
+
|
| 284 |
+
</body>
|
| 285 |
+
</html>
|