feat: publish data engineering chapter
This commit is contained in:
+29
-2
@@ -8,6 +8,7 @@ const routes: Record<string, string> = {
|
||||
roadmap: "/roadmap/",
|
||||
foundations: "/foundations/",
|
||||
scaling: "/scaling/",
|
||||
"pretraining/data": "/pretraining/data/",
|
||||
moe: "/moe/",
|
||||
"long-context": "/long-context/",
|
||||
reasoning: "/reasoning/",
|
||||
@@ -80,6 +81,7 @@ const paths = [
|
||||
<a class="button" href="/k3/">直接解剖 K3</a>
|
||||
<a class="button" href="/deepseek/">DeepSeek 专题</a>
|
||||
<a class="button" href="/scaling/">Scaling Laws 专题</a>
|
||||
<a class="button" href="/pretraining/data/">数据工程专题</a>
|
||||
<a class="button" href="/moe/">MoE 专题</a>
|
||||
<a class="button" href="/long-context/">长上下文专题</a>
|
||||
<a class="button" href="/reasoning/">推理专题</a>
|
||||
@@ -93,20 +95,36 @@ const paths = [
|
||||
<div class="hero-stats">
|
||||
<div><b>16</b><span>核心专题</span></div>
|
||||
<div><b>151</b><span>K3 报告来源</span></div>
|
||||
<div><b>182</b><span>关键论文索引</span></div>
|
||||
<div><b>202</b><span>关键论文索引</span></div>
|
||||
<div><b>47p</b><span>K3 技术报告</span></div>
|
||||
</div>
|
||||
</aside>
|
||||
</div>
|
||||
<div class="scope-strip">
|
||||
<span>研究范围</span>
|
||||
<p>表示学习 · Transformer · Scaling · MoE · 长上下文 · 训练系统 · 后训练 · 推理 · Agent · 多模态 · 服务与评测</p>
|
||||
<p>表示学习 · Transformer · Scaling · 数据工程 · MoE · 长上下文 · 训练系统 · 后训练 · 推理 · Agent · 多模态 · 服务与评测</p>
|
||||
<a href="/progress/">查看实时进度 →</a>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section class="section compact release-section" id="new-chapters">
|
||||
<div class="release-grid">
|
||||
<a class="release-card data-release" href="/pretraining/data/">
|
||||
<div>
|
||||
<p class="eyebrow"><span>NEW / CHAPTER 05</span> DATA & PRE-TRAINING</p>
|
||||
<h2>同样一万亿 Token,可以是完全不同的训练经历</h2>
|
||||
<p>
|
||||
用来源、解析、质量、唯一性、污染、混合、变换、Tokenizer、Packing、课程与模型感知价值十二张账,
|
||||
从 C4、Pile、DoReMi 和 DCLM 一路走到 DeepSeek 五代数据工程与 Kimi K2→K3 原生多模态。
|
||||
</p>
|
||||
</div>
|
||||
<dl>
|
||||
<div><dt>LINEAGE</dt><dd>2019 → 2026</dd></div>
|
||||
<div><dt>PAPERS</dt><dd>31 个一手节点</dd></div>
|
||||
<div><dt>LAB</dt><dd>流水线 · 去重 · 混合 · 改写</dd></div>
|
||||
</dl>
|
||||
<span class="release-arrow" aria-hidden="true">进入数据工程专题 →</span>
|
||||
</a>
|
||||
<a class="release-card scaling-release" href="/scaling/">
|
||||
<div>
|
||||
<p class="eyebrow"><span>NEW / CHAPTER 04</span> SCALING LAWS</p>
|
||||
@@ -420,6 +438,7 @@ const paths = [
|
||||
transition: transform 180ms ease, border-color 180ms ease;
|
||||
}
|
||||
|
||||
.data-release,
|
||||
.scaling-release,
|
||||
.training-release,
|
||||
.reasoning-release {
|
||||
@@ -427,6 +446,13 @@ const paths = [
|
||||
min-height: 510px;
|
||||
}
|
||||
|
||||
.data-release {
|
||||
background:
|
||||
radial-gradient(circle at 82% 18%, rgba(76, 118, 112, 0.2), transparent 30%),
|
||||
repeating-linear-gradient(0deg, transparent 0 46px, rgba(76, 118, 112, 0.045) 46px 47px),
|
||||
var(--paper-raised);
|
||||
}
|
||||
|
||||
.scaling-release {
|
||||
background:
|
||||
radial-gradient(circle at 82% 18%, rgba(159, 91, 52, 0.18), transparent 30%),
|
||||
@@ -510,6 +536,7 @@ const paths = [
|
||||
padding-bottom: 76px;
|
||||
}
|
||||
|
||||
.data-release,
|
||||
.scaling-release,
|
||||
.training-release,
|
||||
.reasoning-release {
|
||||
|
||||
Reference in New Issue
Block a user