feat: add AttnRes gradient scale lab
This commit is contained in:
@@ -2,6 +2,7 @@
|
||||
import BaseLayout from "@/layouts/BaseLayout.astro";
|
||||
import ArchitectureExplorer from "@/components/ArchitectureExplorer.astro";
|
||||
import K3ArtifactLab from "@/components/K3ArtifactLab.astro";
|
||||
import K3AttnResGradientLab from "@/components/K3AttnResGradientLab.astro";
|
||||
import K3AttnResTraceLab from "@/components/K3AttnResTraceLab.astro";
|
||||
import K3ReportLab from "@/components/K3ReportLab.astro";
|
||||
import { k3FigureAtlas, k3Ledgers, k3PaperChain, k3ReportMap } from "@/data/k3";
|
||||
@@ -38,7 +39,8 @@ const toc = [
|
||||
["28", "lab", "八联交互实验"],
|
||||
["29", "artifacts", "开放权重工件审计"],
|
||||
["30", "attnres-reduced", "AttnRes 缩小机制实验"],
|
||||
["31", "audit", "21 张图表审计"],
|
||||
["31", "attnres-gradient", "梯度定义与深度扩展"],
|
||||
["32", "audit", "21 张图表审计"],
|
||||
["↳", "papers", "100 节点阅读链"],
|
||||
];
|
||||
|
||||
@@ -107,13 +109,13 @@ const paperGroups = [
|
||||
|
||||
<BaseLayout
|
||||
title="Kimi K3 技术报告完整深读:架构、训练、RL、系统与评测"
|
||||
description="用三十二张问题账、二十一张图表审计、八个机制实验、四个开放工件视图、五个 AttnRes 独立实验视图与一百个一手阅读节点,逐节读懂 Kimi K3。"
|
||||
description="用三十二张问题账、二十一张图表审计、八个机制实验、四个开放工件视图、两轮十个 AttnRes 独立实验视图与一百个一手阅读节点,逐节读懂 Kimi K3。"
|
||||
section="k3"
|
||||
>
|
||||
<header class="page-hero k3-hero">
|
||||
<div class="page-hero-inner">
|
||||
<div>
|
||||
<p class="eyebrow"><span>ANCHOR REPORT / ROUND 04</span> KIMI K3 · REPORT → ARTIFACTS → INDEPENDENT PROBE</p>
|
||||
<p class="eyebrow"><span>ANCHOR REPORT / ROUND 05</span> KIMI K3 · REPORT → ARTIFACTS → INDEPENDENT PROBE</p>
|
||||
<h1>不把报告压成摘要<br />把每个因果环节<br />重新展开</h1>
|
||||
<p class="lead">
|
||||
K3 同时扩展序列、深度、宽度、视觉与 Agent 轨迹。真正值得读的不是 2.8T 这个最大数字,
|
||||
@@ -123,11 +125,11 @@ const paperGroups = [
|
||||
<dl class="page-facts">
|
||||
<div><dt>QUESTIONS</dt><dd>32 张问题账</dd></div>
|
||||
<div><dt>REPORT</dt><dd>16 Figures · 5 Tables</dd></div>
|
||||
<div><dt>LABS</dt><dd>8 + 4 + 5 个交互视图</dd></div>
|
||||
<div><dt>LABS</dt><dd>8 + 4 + 5 + 5 个交互视图</dd></div>
|
||||
<div><dt>READING</dt><dd>100 个一手 / 官方节点</dd></div>
|
||||
<div><dt>MODEL</dt><dd>2.78T total / 104.2B active</dd></div>
|
||||
<div><dt>ARTIFACTS</dt><dd>96 shards · 497,220 tensors</dd></div>
|
||||
<div><dt>STATUS</dt><dd>K3 四轮 · AttnRes 实验</dd></div>
|
||||
<div><dt>STATUS</dt><dd>K3 五轮 · 梯度定义闭环</dd></div>
|
||||
</dl>
|
||||
</div>
|
||||
</header>
|
||||
@@ -892,12 +894,36 @@ const paperGroups = [
|
||||
<a class="button primary" href="https://git.k1412.top/wuyang/llm-atlas/src/branch/main/research/K3_ATTNRES_REDUCED_AUDIT.md">阅读完整研究审计</a>
|
||||
<a class="button" href="https://git.k1412.top/wuyang/llm-atlas/src/branch/main/experiments/k3/attnres">复跑公开实验代码</a>
|
||||
<a class="button" href="https://arxiv.org/abs/2603.15031">Attention Residuals 原论文</a>
|
||||
<a class="button" href="https://github.com/MoonshotAI/Attention-Residuals">官方实现</a>
|
||||
<a class="button" href="https://github.com/MoonshotAI/Attention-Residuals">官方论文工件</a>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section class="article-section" id="attnres-gradient">
|
||||
<p class="eyebrow"><span>31</span> GRADIENT DEFINITION × DEPTH SCALE</p>
|
||||
<h2>“论文说梯度更均匀”,和上一轮参数梯度反结果,测的是同一件事吗?</h2>
|
||||
<p class="lede">
|
||||
第五轮先审计 Attention Residuals 官方论文与仓库:Figure 5(c) 没有公开 gradient tensor、
|
||||
norm、reduction、diagnostic batch、AMP / clipping 时点或统计代码。本站因此冻结一个可复现的
|
||||
post-MLP output activation-gradient 定义,把深度扩到 16 / 32 blocks、预算扩到 8,000 steps,
|
||||
再用三 seed 检查“首尾平衡”和“全层离散度”是否真的同方向。
|
||||
</p>
|
||||
<div class="artifact-callout">
|
||||
<article><span>F / FROZEN</span><b>12 × 8,000 steps</b><p>786,432,000 formal target bytes;两深度、两结构、三 seed。</p></article>
|
||||
<article><span>X / OBSERVED</span><b>first/last 6 / 6 改善</b><p>depth-16 平均 61.0%;depth-32 平均 72.0%。</p></article>
|
||||
<article class="warning"><span>X / COUNTEREVIDENCE</span><b>CV 6 / 6 恶化</b><p>局部尖峰让 depth-16 / 32 平均相对恶化 10.3% / 60.0%。</p></article>
|
||||
<article><span>R / REPLAY</span><b>model + optimizer exact</b><p>指定 32-layer Block 格从零重训 8,000 steps,冻结字段逐项一致。</p></article>
|
||||
</div>
|
||||
<K3AttnResGradientLab />
|
||||
<div class="hero-actions">
|
||||
<a class="button primary" href="https://git.k1412.top/wuyang/llm-atlas/src/branch/main/research/K3_ATTNRES_GRADIENT_SCALE_AUDIT.md">阅读完整结果审计</a>
|
||||
<a class="button" href="https://git.k1412.top/wuyang/llm-atlas/src/branch/main/research/K3_ATTNRES_GRADIENT_DEFINITION_AUDIT.md">核对论文定义边界</a>
|
||||
<a class="button" href="https://git.k1412.top/wuyang/llm-atlas/src/branch/main/experiments/k3/attnres_gradient">复跑 12 格实验</a>
|
||||
<a class="button" href="https://github.com/MoonshotAI/Attention-Residuals">官方一手工件</a>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section class="article-section" id="audit">
|
||||
<p class="eyebrow"><span>31</span> FIGURE & TABLE AUDIT</p>
|
||||
<p class="eyebrow"><span>32</span> FIGURE & TABLE AUDIT</p>
|
||||
<h2>Figure 1–16、Table 1–5:每张图究竟支持什么,不能支持什么</h2>
|
||||
<div class="figure-atlas">
|
||||
{k3FigureAtlas.map(([id, report, title, contract]) => (
|
||||
|
||||
Reference in New Issue
Block a user