wuyang/llm-atlas
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: trace DeepSeek Chat completion depth

Browse Source
This commit is contained in:
wuyang
2026-07-30 00:24:27 +08:00
parent fb44d15bb8
commit 8bb488f275
23 changed files with 1507052 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/components/DeepSeekCompletionDepthLab.astro
+851
View File
@@ -0,0 +1,851 @@
---
import rawLab from "@/data/deepseek-v2-lite-chat-completion-depth-compact.json";
const lab = rawLab as any;
const json = JSON.stringify(lab).replaceAll("<", "\\u003c");
const conditions = [
"s0_eos",
"s1_eos",
"s0_bos",
"s1_bos",
"s0_x",
"s1_x",
"s0_period",
"s1_period",
];
const conditionLabels: Record<string, string> = {
s0_eos: "S0 · EOS",
s1_eos: "S1 · EOS",
s0_bos: "S0 · BOS",
s1_bos: "S1 · BOS",
s0_x: "S0 · x",
s1_x: "S1 · x",
s0_period: "S0 · 句点",
s1_period: "S1 · 句点",
};
const firstHidden = lab.depth.hiddenSeries.all.system_eos;
const firstRouter = lab.depth.routerSeries.all.system_eos;
const shortStage = (stage: string) => (
stage === "embedding"
? "E"
: stage === "final_norm"
? "N"
: `L${Number(stage.slice(-2))}`
);
---
<figure class="completion-depth-lab" data-completion-depth-lab>
<header class="cd-head">
<div>
<p>ROUND 05 / COMPLETION × FULL DEPTH</p>
<h3>一句输出怎样穿过 27 层：完成、答对、表示、路由分四张账</h3>
</div>
<p>
同一官方 SFT Chat checkpoint、同 16 条完整 source、同八格输入。
先把统一预算升到 512，再沿 embedding → 27 decoder layers → final norm
追踪隐藏状态，并读取 26 个 MoE gate。每个数字都能回到原始 JSON 与独立复跑。
</p>
</header>
<div class="cd-ledger">
<article class="pass"><span>512 · NATURAL EOS</span><b>121 / 128</b><p>128-token 时只有 31 / 128</p></article>
<article><span>MATH · STRICT</span><b>23 / 32</b><p>4 tasks × 8 conditions</p></article>
<article><span>CODE · TESTS PASS</span><b>24 / 32</b><p>官方 HumanEval tests</p></article>
<article><span>HIDDEN TRACE</span><b>29 stages</b><p>embedding + 27 layers + norm</p></article>
<article><span>ROUTER TRACE</span><b>1,918,176</b><p>target top-6 decisions</p></article>
<article class="pass"><span>FRESH-PROCESS RERUN</span><b>5,184 hashes</b><p>hidden + route + weights exact</p></article>
</div>
<div class="cd-tabs" role="tablist" aria-label="选择完整生成与深度追踪视图">
<button type="button" role="tab" data-cd-tab="completion" aria-selected="true">
<span>01</span><b>完成度阶梯</b><small>128 → 512</small>
</button>
<button type="button" role="tab" data-cd-tab="tasks" aria-selected="false" tabindex="-1">
<span>02</span><b>答案真的对吗</b><small>Math + Code</small>
</button>
<button type="button" role="tab" data-cd-tab="hidden" aria-selected="false" tabindex="-1">
<span>03</span><b>表示怎样分叉</b><small>29 hidden stages</small>
</button>
<button type="button" role="tab" data-cd-tab="router" aria-selected="false" tabindex="-1">
<span>04</span><b>专家怎样换路</b><small>26 MoE gates</small>
</button>
</div>
<section class="cd-panel" data-cd-panel="completion">
<div class="cd-panel-lead">
<div><span>I / STOPPING LEDGER</span><h4>长度上限不是 EOS，更不是错误答案</h4></div>
<p>
两次运行都对全部 128 格使用统一预算；不是只给先前截断的 97 格“续杯”。
512 解决了大部分截断，但仍有 7 格没有自然结束。
</p>
</div>
<div class="budget-ladder" aria-label="128 与 512 token 完成度比较">
{lab.completion.budgetLadder.map((budget: any) => (
<article>
<header><span>MAX NEW TOKENS</span><b>{budget.maxNewTokens}</b></header>
<div class="budget-track">
<i style={`--complete:${budget.naturalEos / budget.outputs * 100}%`}></i>
</div>
<dl>
<div><dt>NATURAL EOS</dt><dd>{budget.naturalEos} / {budget.outputs}</dd></div>
<div><dt>BUDGET TRUNCATED</dt><dd>{budget.truncated} / {budget.outputs}</dd></div>
</dl>
</article>
))}
<div class="budget-arrow"><span>统一重跑</span><b>+90</b><small>新增自然 EOS</small></div>
</div>
<div class="condition-table">
<header><b>CONDITION</b><b>NATURAL EOS</b><b>MEAN TOKENS</b><b>MATH STRICT</b><b>CODE PASS</b></header>
{conditions.map((condition) => {
const row = lab.completion.summary.by_condition[condition];
return (
<div data-completion-condition={condition}>
<span>{conditionLabels[condition]}</span>
<b class={row.natural_eos === 16 ? "good" : ""}>{row.natural_eos} / 16</b>
<b>{row.mean_generated_tokens.toFixed(1)}</b>
<b>{row.math_strict_complete_exact} / {row.math_sources}</b>
<b>{row.code_tests_pass} / {row.code_sources}</b>
</div>
);
})}
</div>
<div class="incomplete-ledger">
<header><span>仍未解决的 7 格</span><p>6 个 English continuation + 1 个未闭合的 HumanEval code fence</p></header>
<div>
{lab.completion.incompleteRows.map((row: any) => (
<article>
<b>{row.sourceId}</b>
<span>{conditionLabels[row.condition]} · {row.generatedTokens} tokens</span>
<em>{row.domain === "code" ? "AST FAIL · NOT RUN" : "NO EOS"}</em>
</article>
))}
</div>
</div>
<div class="prefix-gate">
<article><span>BASELINE PROMPT HASH</span><b>128 / 128 EXACT</b><p>输入身份没有漂移</p></article>
<article><span>FIRST 128 GENERATED TOKENS</span><b>128 / 128 EXACT</b><p>512 运行完整复现短预算前缀</p></article>
<article><span>INDEPENDENT LONG RERUN</span><b>32 / 32 EXACT</b><p>完整 token IDs、文本与停止状态</p></article>
</div>
</section>
<section class="cd-panel" data-cd-panel="tasks" hidden>
<div class="cd-panel-lead">
<div><span>II / TASK LEDGER</span><h4>把“可解析”与“通过官方测试”分开</h4></div>
<p>
数学按 final marker 优先抽取，最后数字只作 fallback；代码先抽取与 AST parse，
再逐 candidate 进入无网络、只读、无 host mount 的新容器。
</p>
</div>
<div class="task-control">
<label>
<span>选择八格条件</span>
<select data-task-condition aria-label="选择任务评测条件">
{conditions.map((condition) => (
<option value={condition}>{conditionLabels[condition]}</option>
))}
</select>
</label>
<div>
<span>读格子</span>
<p><i class="pass"></i>通过 / exact <i class="fail"></i>执行但失败 <i class="warn"></i>fallback 或未执行</p>
</div>
</div>
<div class="task-columns">
<article>
<header><span>GSM8K · 4 SOURCES</span><b data-math-condition-total>—</b></header>
<div class="task-grid" data-math-task-grid></div>
<div class="task-summary">
<div><span>STRICT EXACT / ALL CELLS</span><b>{lab.completion.taskTotals.math.strictCorrect} / 32</b></div>
<p>20 boxed · 8 answer phrase · 4 last-number fallback</p>
</div>
</article>
<article>
<header><span>HUMANEVAL · 4 SOURCES</span><b data-code-condition-total>—</b></header>
<div class="task-grid" data-code-task-grid></div>
<div class="task-summary">
<div><span>OFFICIAL TESTS PASS / ALL CELLS</span><b>{lab.completion.taskTotals.code.testsPassed} / 32</b></div>
<p>24 pass · 5 assertion · 2 runtime · 1 not run</p>
</div>
</article>
</div>
<div class="sandbox-flow">
<article><span>01 / EXTRACT</span><b>final marker / code fence</b><p>gold 与 tests 从不进入 prompt</p></article>
<i>→</i>
<article><span>02 / STATIC</span><b>Decimal / Python AST</b><p>先确认结果能被判定</p></article>
<i>→</i>
<article class="active"><span>03 / FRESH CONTAINER</span><b>network none · read-only</b><p>65534 · cap drop ALL · no mounts</p></article>
<i>→</i>
<article><span>04 / OFFICIAL CHECK</span><b>5s · 256MiB · 0.5 CPU</b><p>pass 只是功能证据，不是安全证明</p></article>
</div>
</section>
<section class="cd-panel" data-cd-panel="hidden" hidden>
<div class="cd-panel-lead">
<div><span>III / REPRESENTATION DEPTH</span><h4>目标 token 相同，何时开始“不再是同一个状态”</h4></div>
<p>
embedding 是逐 token lookup，所以 10 条 edge 的 15,370 个目标行全部 exact；
进入 layer 00 后，前文开始通过 attention 混入，十条 edge 的 exact rows 都变成 0。
</p>
</div>
<div class="depth-controls">
<label><span>对比边</span><select data-hidden-edge aria-label="选择隐藏状态对比边">
{lab.contract.edgeOrder.map((edge: string) => (
<option value={edge}>{lab.contract.edgeLabels[edge]}</option>
))}
</select></label>
<label><span>聚合域</span><select data-hidden-domain aria-label="选择隐藏状态聚合域">
<option value="all">四域合计 · n=16</option>
<option value="english">English · n=4</option>
<option value="chinese">Chinese · n=4</option>
<option value="code">Code · n=4</option>
<option value="math">Math · n=4</option>
</select></label>
<label><span>纵轴</span><select data-hidden-metric aria-label="选择隐藏状态指标">
<option value="divergence">1 − cosine · %</option>
<option value="relative">relative L2 · %</option>
<option value="maxabs">max absolute delta</option>
</select></label>
</div>
<div class="depth-chart">
<header><span data-hidden-chart-title>System on − off · EOS</span><b data-hidden-chart-domain>四域合计</b></header>
<svg viewBox="0 0 840 270" role="img" aria-label="29 个隐藏状态阶段的差异曲线">
<g class="chart-grid">
<line x1="42" y1="34" x2="820" y2="34"></line>
<line x1="42" y1="126" x2="820" y2="126"></line>
<line x1="42" y1="218" x2="820" y2="218"></line>
</g>
<text x="4" y="38" data-hidden-ymax>—</text>
<text x="4" y="130" data-hidden-ymid>—</text>
<text x="18" y="222">0</text>
<polyline data-hidden-line points="" />
<circle data-hidden-focus cx="42" cy="218" r="5" />
<text x="42" y="249">E</text><text x="70" y="249">L0</text>
<text x="182" y="249">L4</text><text x="294" y="249">L8</text>
<text x="406" y="249">L12</text><text x="518" y="249">L16</text>
<text x="630" y="249">L20</text><text x="742" y="249">L24</text>
<text x="808" y="249">N</text>
</svg>
</div>
<div class="depth-strip" data-hidden-strip>
{firstHidden.map((row: any, index: number) => (
<button type="button" data-hidden-stage={index} title={row.stage}>
<span>{shortStage(row.stage)}</span><i></i>
</button>
))}
</div>
<div class="depth-reading">
<article><span>SELECTED STAGE</span><b data-hidden-stage-name>embedding</b><p data-hidden-stage-note>逐 token lookup；目标 IDs 相同</p></article>
<article><span>MEAN COSINE</span><b data-hidden-cosine>1.000000</b><p>token-weighted</p></article>
<article><span>MEAN RELATIVE L2</span><b data-hidden-relative>0.0000%</b><p>4/16 source mean</p></article>
<article><span>EXACT ROWS</span><b data-hidden-exact>1,537 / 1,537</b><p>byte-exact BF16 rows</p></article>
<article><span>MAX |Δ|</span><b data-hidden-maxabs>0</b><p>本阶段目标内容范围</p></article>
</div>
<div class="depth-boundary">
<b>为什么只看 interior content token</b>
<p>
tokenizer 有 56 个 token 横跨字符边界，已排除；留下的 1,537 个 token / condition
在八格中 ID 序列完全一致。否则“同位置”未必是“同 token”。
</p>
</div>
</section>
<section class="cd-panel" data-cd-panel="router" hidden>
<div class="cd-panel-lead">
<div><span>IV / ROUTER DEPTH</span><h4>表示轻微转动，也可能换掉 top-6 专家排序</h4></div>
<p>
ordered exact 要求六个专家与顺序都相同；set exact 只要求集合相同；
weighted TV 还读取门控权重。三者回答不同问题，不能只挑一列讲故事。
</p>
</div>
<div class="depth-controls">
<label><span>对比边</span><select data-router-edge aria-label="选择路由对比边">
{lab.contract.edgeOrder.map((edge: string) => (
<option value={edge}>{lab.contract.edgeLabels[edge]}</option>
))}
</select></label>
<label><span>聚合域</span><select data-router-domain aria-label="选择路由聚合域">
<option value="all">四域合计 · n=16</option>
<option value="english">English · n=4</option>
<option value="chinese">Chinese · n=4</option>
<option value="code">Code · n=4</option>
<option value="math">Math · n=4</option>
</select></label>
<label><span>纵轴</span><select data-router-metric aria-label="选择路由指标">
<option value="ordered">ordered top-6 divergence · %</option>
<option value="set">expert-set divergence · %</option>
<option value="weighted">token-weighted TV · %</option>
<option value="load">aggregate load TV · %</option>
</select></label>
</div>
<div class="depth-chart router-chart">
<header><span data-router-chart-title>System on − off · EOS</span><b data-router-chart-domain>四域合计</b></header>
<svg viewBox="0 0 840 270" role="img" aria-label="26 个 MoE gate 的路由差异曲线">
<g class="chart-grid">
<line x1="42" y1="34" x2="820" y2="34"></line>
<line x1="42" y1="126" x2="820" y2="126"></line>
<line x1="42" y1="218" x2="820" y2="218"></line>
</g>
<text x="4" y="38" data-router-ymax>—</text>
<text x="4" y="130" data-router-ymid>—</text>
<text x="18" y="222">0</text>
<polyline data-router-line points="" />
<circle data-router-focus cx="42" cy="218" r="5" />
<text x="42" y="249">L1</text><text x="162" y="249">L5</text>
<text x="312" y="249">L10</text><text x="462" y="249">L15</text>
<text x="612" y="249">L20</text><text x="762" y="249">L25</text>
</svg>
</div>
<div class="depth-strip router-strip" data-router-strip>
{firstRouter.map((row: any, index: number) => (
<button type="button" data-router-layer={index} title={row.layer}>
<span>L{index + 1}</span><i></i>
</button>
))}
</div>
<div class="depth-reading router-reading">
<article><span>SELECTED GATE</span><b data-router-layer-name>layer 01</b><p>64 routed experts · top-6</p></article>
<article><span>ORDERED EXACT</span><b data-router-ordered>—</b><p>六个专家及顺序完全相同</p></article>
<article><span>SET EXACT</span><b data-router-set>—</b><p>忽略六个专家的顺序</p></article>
<article><span>MEAN JACCARD</span><b data-router-jaccard>—</b><p>逐 token 专家集合</p></article>
<article><span>WEIGHTED TV</span><b data-router-tv>—</b><p>top-6 门控质量变化</p></article>
</div>
<div class="repro-proof">
<article class="pass"><span>HIDDEN TENSOR HASHES</span><b>1,856 / 1,856</b><p>target + full input · fresh process</p></article>
<article class="pass"><span>ORDERED ROUTE HASHES</span><b>1,664 / 1,664</b><p>26 gates × 8 cells × 2 scopes × 4</p></article>
<article class="pass"><span>ROUTE-WEIGHT HASHES</span><b>1,664 / 1,664</b><p>BF16 gate weights exact</p></article>
<article><span>CLAIM BOUNDARY</span><b>association ≠ mediation</b><p>路由分叉不能自动解释输出或能力</p></article>
</div>
<div class="artifact-links">
<a href="https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat" rel="noreferrer">官方 Chat checkpoint ↗</a>
<a href="https://git.k1412.top/wuyang/llm-atlas/src/branch/main/src/data/deepseek-v2-lite-chat-completion-512.json" rel="noreferrer">512 正式 generation JSON ↗</a>
<a href="https://git.k1412.top/wuyang/llm-atlas/src/branch/main/src/data/deepseek-v2-lite-chat-full-depth.json" rel="noreferrer">36MB 全深度原始 JSON ↗</a>
<a href="https://git.k1412.top/wuyang/llm-atlas/src/branch/main/research/DEEPSEEK_V2_LITE_CHAT_COMPLETION_DEPTH_AUDIT.md" rel="noreferrer">完整审计与非结论 ↗</a>
</div>
</section>
<figcaption>
<span>X / OFFICIAL BF16 CHAT · COMPLETION-AWARE FULL-DEPTH TRACE</span>
revision <code>{lab.model.revision}</code>；512 formal
<code>{lab.artifacts.completion.sha256.slice(0, 16)}…</code>；
full-depth formal <code>{lab.artifacts.depth.sha256.slice(0, 16)}…</code>。
四域各 4 条是机制显微镜，不是 benchmark。
</figcaption>
<script is:inline type="application/json" data-cd-data set:html={json}></script>
</figure>
<script>
const cdRoots = document.querySelectorAll<HTMLElement>(
"[data-completion-depth-lab]",
);
const cdDomainLabels: Record<string, string> = {
all: "四域合计",
english: "English · n=4",
chinese: "Chinese · n=4",
code: "Code · n=4",
math: "Math · n=4",
};
cdRoots.forEach((root) => {
const payload = root.querySelector<HTMLScriptElement>("[data-cd-data]");
if (!payload) return;
const data = JSON.parse(payload.textContent ?? "{}");
const one = <T extends Element>(selector: string) => (
root.querySelector<T>(selector)
);
const all = <T extends Element>(selector: string) => (
[...root.querySelectorAll<T>(selector)]
);
const set = (selector: string, value: string) => {
const node = one<HTMLElement>(selector);
if (node) node.textContent = value;
};
const percent = (value: number, digits = 1) => (
`${(value * 100).toFixed(digits)}%`
);
const tabs = all<HTMLButtonElement>("[data-cd-tab]");
const panels = all<HTMLElement>("[data-cd-panel]");
const selectTab = (tab: HTMLButtonElement) => {
tabs.forEach((candidate) => {
const active = candidate === tab;
candidate.setAttribute("aria-selected", String(active));
candidate.tabIndex = active ? 0 : -1;
});
panels.forEach((panel) => {
panel.hidden = panel.dataset.cdPanel !== tab.dataset.cdTab;
});
};
tabs.forEach((tab, index) => {
tab.addEventListener("click", () => selectTab(tab));
tab.addEventListener("keydown", (event) => {
if (!["ArrowLeft", "ArrowRight", "Home", "End"].includes(event.key)) {
return;
}
event.preventDefault();
let next = index;
if (event.key === "ArrowRight") next = (index + 1) % tabs.length;
if (event.key === "ArrowLeft") {
next = (index - 1 + tabs.length) % tabs.length;
}
if (event.key === "Home") next = 0;
if (event.key === "End") next = tabs.length - 1;
tabs[next].focus();
selectTab(tabs[next]);
});
});
const taskCondition = one<HTMLSelectElement>("[data-task-condition]");
const taskRows = data.completion.taskRows;
const taskClass = (row: any) => {
if (row.domain === "math") {
if (row.taskEvaluation.strict_complete_numeric_exact) return "pass";
if (
row.taskEvaluation.fixed_budget_numeric_exact
|| row.taskEvaluation.extraction_method === "last_number_fallback"
) return "warn";
return "fail";
}
const status = row.taskEvaluation.execution?.status;
if (status === "passed") return "pass";
if (status === "not_run") return "warn";
return "fail";
};
const taskLabel = (row: any) => {
if (row.domain === "math") {
const evaluation = row.taskEvaluation;
if (evaluation.strict_complete_numeric_exact) {
return `${evaluation.predicted_final} · EXACT`;
}
if (evaluation.predicted_final != null) {
return `${evaluation.predicted_final} · WRONG/FALLBACK`;
}
return "UNRESOLVED";
}
return (row.taskEvaluation.execution?.status ?? "not_run")
.replaceAll("_", " ")
.toUpperCase();
};
const renderTaskGrid = (
domain: "math" | "code",
selector: string,
totalSelector: string,
) => {
const condition = taskCondition?.value ?? "s0_eos";
const rows = taskRows.filter(
(row: any) => (
row.domain === domain && row.condition === condition
),
);
const container = one<HTMLElement>(selector);
if (!container) return;
container.replaceChildren(...rows.map((row: any) => {
const article = document.createElement("article");
article.className = taskClass(row);
const source = document.createElement("b");
source.textContent = row.sourceId;
const result = document.createElement("span");
result.textContent = taskLabel(row);
const completion = document.createElement("em");
completion.textContent = row.hitEos
? `${row.generatedTokens} TOKENS · EOS`
: `${row.generatedTokens} TOKENS · TRUNCATED`;
article.append(source, result, completion);
return article;
}));
const passing = rows.filter((row: any) => taskClass(row) === "pass").length;
set(totalSelector, `${passing} / ${rows.length} PASS`);
};
const renderTasks = () => {
renderTaskGrid(
"math",
"[data-math-task-grid]",
"[data-math-condition-total]",
);
renderTaskGrid(
"code",
"[data-code-task-grid]",
"[data-code-condition-total]",
);
};
taskCondition?.addEventListener("change", renderTasks);
type ChartConfig = {
kind: "hidden" | "router";
edge: HTMLSelectElement | null;
domain: HTMLSelectElement | null;
metric: HTMLSelectElement | null;
line: SVGPolylineElement | null;
focus: SVGCircleElement | null;
strip: HTMLElement | null;
selected: number;
};
const hiddenChart: ChartConfig = {
kind: "hidden",
edge: one("[data-hidden-edge]"),
domain: one("[data-hidden-domain]"),
metric: one("[data-hidden-metric]"),
line: one("[data-hidden-line]"),
focus: one("[data-hidden-focus]"),
strip: one("[data-hidden-strip]"),
selected: 0,
};
const routerChart: ChartConfig = {
kind: "router",
edge: one("[data-router-edge]"),
domain: one("[data-router-domain]"),
metric: one("[data-router-metric]"),
line: one("[data-router-line]"),
focus: one("[data-router-focus]"),
strip: one("[data-router-strip]"),
selected: 0,
};
const chartValues = (chart: ChartConfig, rows: any[]) => {
const metric = chart.metric?.value;
if (chart.kind === "hidden") {
if (metric === "relative") {
return rows.map((row) => row.meanRelativeL2 * 100);
}
if (metric === "maxabs") {
return rows.map((row) => row.maxAbsDelta);
}
return rows.map((row) => (1 - row.meanCosine) * 100);
}
if (metric === "set") {
return rows.map((row) => (1 - row.setExactRate) * 100);
}
if (metric === "weighted") {
return rows.map((row) => row.meanTokenWeightedTv * 100);
}
if (metric === "load") {
return rows.map((row) => row.meanAggregateLoadTv * 100);
}
return rows.map((row) => (1 - row.orderedExactRate) * 100);
};
const chartRows = (chart: ChartConfig) => {
const edge = chart.edge?.value ?? "system_eos";
const domain = chart.domain?.value ?? "all";
return chart.kind === "hidden"
? data.depth.hiddenSeries[domain][edge]
: data.depth.routerSeries[domain][edge];
};
const renderChart = (chart: ChartConfig) => {
const rows = chartRows(chart);
const values = chartValues(chart, rows);
const maxValue = Math.max(...values, 0.000001) * 1.12;
const x = (index: number) => (
42 + index * 778 / Math.max(1, rows.length - 1)
);
const y = (value: number) => 218 - value / maxValue * 184;
chart.line?.setAttribute(
"points",
values.map((value: number, index: number) => (
`${x(index).toFixed(2)},${y(value).toFixed(2)}`
)).join(" "),
);
const selected = Math.min(chart.selected, rows.length - 1);
chart.focus?.setAttribute("cx", x(selected).toFixed(2));
chart.focus?.setAttribute("cy", y(values[selected]).toFixed(2));
const prefix = chart.kind === "hidden" ? "hidden" : "router";
set(
`[data-${prefix}-ymax]`,
maxValue >= 10 ? maxValue.toFixed(0) : maxValue.toFixed(2),
);
set(
`[data-${prefix}-ymid]`,
maxValue >= 10
? (maxValue / 2).toFixed(0)
: (maxValue / 2).toFixed(2),
);
set(
`[data-${prefix}-chart-title]`,
data.contract.edgeLabels[chart.edge?.value ?? "system_eos"],
);
set(
`[data-${prefix}-chart-domain]`,
cdDomainLabels[chart.domain?.value ?? "all"],
);
const buttons = [
...(chart.strip?.querySelectorAll<HTMLButtonElement>("button") ?? []),
];
buttons.forEach((button, index) => {
const level = Math.max(0.04, values[index] / maxValue);
button.style.setProperty("--level", String(level));
button.classList.toggle("selected", index === selected);
const bar = button.querySelector<HTMLElement>("i");
if (bar) bar.style.height = `${Math.max(4, level * 100)}%`;
});
const row = rows[selected];
if (chart.kind === "hidden") {
set("[data-hidden-stage-name]", row.stage);
set("[data-hidden-stage-note]", row.stage === "embedding"
? "逐 token lookup；目标 IDs 相同"
: "上下文已通过 attention / residual 混入");
set("[data-hidden-cosine]", row.meanCosine.toFixed(6));
set("[data-hidden-relative]", percent(row.meanRelativeL2, 2));
set(
"[data-hidden-exact]",
`${row.exactRows.toLocaleString()} / ${row.tokens.toLocaleString()}`,
);
set("[data-hidden-maxabs]", row.maxAbsDelta.toFixed(5));
} else {
set("[data-router-layer-name]", row.layer.replace("_", " "));
set(
"[data-router-ordered]",
`${row.orderedExact.toLocaleString()} / ${row.tokens.toLocaleString()} · ${percent(row.orderedExactRate)}`,
);
set(
"[data-router-set]",
`${row.setExact.toLocaleString()} / ${row.tokens.toLocaleString()} · ${percent(row.setExactRate)}`,
);
set("[data-router-jaccard]", row.meanSetJaccard.toFixed(5));
set("[data-router-tv]", percent(row.meanTokenWeightedTv, 2));
}
};
for (const chart of [hiddenChart, routerChart]) {
chart.edge?.addEventListener("change", () => renderChart(chart));
chart.domain?.addEventListener("change", () => renderChart(chart));
chart.metric?.addEventListener("change", () => renderChart(chart));
const attribute = chart.kind === "hidden"
? "data-hidden-stage"
: "data-router-layer";
chart.strip?.querySelectorAll<HTMLButtonElement>("button").forEach(
(button) => {
button.addEventListener("click", () => {
chart.selected = Number(button.getAttribute(attribute));
renderChart(chart);
});
},
);
}
renderTasks();
renderChart(hiddenChart);
renderChart(routerChart);
});
</script>
<style>
.completion-depth-lab {
margin: 2.2rem 0 0;
overflow: hidden;
border: 1px solid rgba(30, 38, 43, .16);
background: #f7f4ec;
box-shadow: 0 28px 70px rgba(22, 35, 43, .1);
}
.cd-head {
display: grid;
grid-template-columns: 1fr 1fr;
gap: 2.4rem;
align-items: end;
padding: 2rem;
color: #f8f4e9;
background:
radial-gradient(circle at 76% 24%, rgba(178, 102, 64, .28), transparent 26%),
radial-gradient(circle at 18% 80%, rgba(67, 145, 132, .2), transparent 28%),
linear-gradient(135deg, #172c35, #253f47);
}
.cd-head p { margin: 0; color: rgba(255,255,255,.72); font-size: .77rem; line-height: 1.7; }
.cd-head > div > p { color: #84c6bb; font: 750 .61rem/1.2 var(--font-mono); letter-spacing: .1em; }
.cd-head h3 { max-width: 650px; margin: .75rem 0 0; color: white; font: 760 clamp(1.55rem,3vw,2.45rem)/1.14 var(--font-display); }
.cd-ledger { display: grid; grid-template-columns: repeat(6, 1fr); border-bottom: 1px solid rgba(30,38,43,.14); }
.cd-ledger article { min-width: 0; padding: 1rem; border-right: 1px solid rgba(30,38,43,.12); background: #ece8dd; }
.cd-ledger article:last-child { border-right: 0; }
.cd-ledger article.pass { background: rgba(54,128,108,.12); }
.cd-ledger span,
.task-summary span,
.depth-reading span,
.repro-proof span { display: block; color: #60706e; font: 720 .51rem/1.25 var(--font-mono); letter-spacing: .07em; }
.cd-ledger b { display: block; margin-top: .45rem; color: #182b33; font: 760 .78rem/1.25 var(--font-mono); }
.cd-ledger p { margin: .35rem 0 0; color: #68716f; font-size: .58rem; line-height: 1.4; }
.cd-tabs { display: grid; grid-template-columns: repeat(4, 1fr); border-bottom: 1px solid rgba(30,38,43,.14); }
.cd-tabs button { display: grid; grid-template-columns: auto 1fr; grid-template-rows: auto auto; column-gap: .75rem; min-width: 0; padding: .9rem 1rem; border: 0; border-right: 1px solid rgba(30,38,43,.14); color: #25363c; text-align: left; background: #fbf8f1; cursor: pointer; }
.cd-tabs button:last-child { border-right: 0; }
.cd-tabs button[aria-selected="true"] { color: white; background: #ad5935; }
.cd-tabs span { grid-row: 1 / 3; opacity: .72; font: 720 .55rem/1.2 var(--font-mono); }
.cd-tabs b { min-width: 0; font: 720 .76rem/1.25 var(--font-display); }
.cd-tabs small { opacity: .68; font: .54rem/1.3 var(--font-mono); }
.cd-panel { padding: 1.55rem; }
.cd-panel[hidden] { display: none; }
.cd-panel-lead { display: grid; grid-template-columns: 1fr 1fr; gap: 2rem; align-items: end; margin-bottom: 1.25rem; }
.cd-panel-lead span { color: #a75231; font: 750 .56rem/1.2 var(--font-mono); letter-spacing: .09em; }
.cd-panel-lead h4 { margin: .35rem 0 0; color: #1c3037; font: 750 1.25rem/1.2 var(--font-display); }
.cd-panel-lead p { margin: 0; color: #65716f; font-size: .7rem; line-height: 1.65; }
.budget-ladder { position: relative; display: grid; grid-template-columns: 1fr 1fr; gap: 1px; background: rgba(30,38,43,.15); border: 1px solid rgba(30,38,43,.15); }
.budget-ladder > article { padding: 1.1rem; background: #eeeae0; }
.budget-ladder header { display: flex; justify-content: space-between; align-items: end; }
.budget-ladder header span { color: #697572; font: 700 .52rem/1 var(--font-mono); }
.budget-ladder header b { color: #ad5935; font: 780 1.55rem/1 var(--font-display); }
.budget-track { height: 1rem; margin-top: 1rem; background: rgba(175,83,49,.22); }
.budget-track i { display: block; width: var(--complete); height: 100%; background: #347d6f; }
.budget-ladder dl { display: grid; grid-template-columns: 1fr 1fr; gap: 1px; margin: .8rem 0 0; background: rgba(30,38,43,.1); }
.budget-ladder dl div { padding: .65rem; background: #faf7ef; }
.budget-ladder dt { color: #737c79; font: .48rem/1 var(--font-mono); }
.budget-ladder dd { margin: .35rem 0 0; color: #283c42; font: 740 .7rem/1 var(--font-mono); }
.budget-arrow { position: absolute; top: 50%; left: 50%; z-index: 2; display: grid; place-items: center; width: 5.2rem; height: 5.2rem; transform: translate(-50%,-50%); color: white; border: .35rem solid #f7f4ec; border-radius: 50%; background: #ab5b39; text-align: center; }
.budget-arrow span,
.budget-arrow small { font: .44rem/1.2 var(--font-mono); }
.budget-arrow b { font: 780 1.1rem/1.1 var(--font-display); }
.condition-table { margin-top: 1rem; border: 1px solid rgba(30,38,43,.14); }
.condition-table > header,
.condition-table > div { display: grid; grid-template-columns: 1.25fr repeat(4, 1fr); gap: .7rem; align-items: center; padding: .65rem .8rem; border-bottom: 1px solid rgba(30,38,43,.1); }
.condition-table > header { color: #dfe9e6; background: #27434a; font: 680 .48rem/1.2 var(--font-mono); }
.condition-table > div:last-child { border-bottom: 0; }
.condition-table > div:nth-child(odd) { background: #efebe1; }
.condition-table span { color: #293d42; font: 690 .64rem/1.2 var(--font-mono); }
.condition-table b { color: #596663; font: 680 .6rem/1.2 var(--font-mono); }
.condition-table b.good { color: #277563; }
.incomplete-ledger { margin-top: 1rem; border: 1px solid rgba(164,81,46,.2); background: rgba(178,91,50,.08); }
.incomplete-ledger > header { display: flex; justify-content: space-between; gap: 1rem; padding: .75rem .9rem; color: #653d30; border-bottom: 1px solid rgba(164,81,46,.14); }
.incomplete-ledger > header span { font: 730 .58rem/1.2 var(--font-mono); }
.incomplete-ledger > header p { margin: 0; font-size: .61rem; }
.incomplete-ledger > div { display: grid; grid-template-columns: repeat(4, 1fr); }
.incomplete-ledger article { min-width: 0; padding: .7rem; border-right: 1px solid rgba(164,81,46,.12); border-bottom: 1px solid rgba(164,81,46,.12); }
.incomplete-ledger article b,
.incomplete-ledger article span,
.incomplete-ledger article em { display: block; overflow-wrap: anywhere; }
.incomplete-ledger article b { color: #3b4a4c; font: 670 .56rem/1.3 var(--font-mono); }
.incomplete-ledger article span { margin-top: .35rem; color: #6e706b; font-size: .54rem; }
.incomplete-ledger article em { margin-top: .45rem; color: #a34f30; font: 720 .48rem/1 var(--font-mono); }
.prefix-gate,
.repro-proof { display: grid; grid-template-columns: repeat(3, 1fr); gap: 1px; margin-top: 1rem; background: rgba(30,38,43,.13); border: 1px solid rgba(30,38,43,.13); }
.prefix-gate article,
.repro-proof article { padding: .85rem; background: rgba(54,128,108,.1); }
.prefix-gate span { color: #52716b; font: 710 .5rem/1.2 var(--font-mono); }
.prefix-gate b,
.repro-proof b { display: block; margin-top: .4rem; color: #245d53; font: 760 .72rem/1.2 var(--font-mono); }
.prefix-gate p,
.repro-proof p { margin: .4rem 0 0; color: #68736f; font-size: .58rem; line-height: 1.45; }
.task-control,
.depth-controls { display: grid; grid-template-columns: minmax(14rem,.8fr) 1.2fr; gap: 1px; border: 1px solid rgba(30,38,43,.14); background: rgba(30,38,43,.14); }
.task-control > *,
.depth-controls label { min-width: 0; padding: .75rem; background: #eeeae0; }
.task-control span,
.depth-controls span { display: block; margin-bottom: .4rem; color: #65716f; font: 720 .52rem/1.2 var(--font-mono); }
.task-control select,
.depth-controls select { width: 100%; min-width: 0; padding: .57rem; color: #24383e; border: 1px solid rgba(30,38,43,.2); background: #fffdf8; font: 670 .62rem/1.3 var(--font-mono); }
.task-control p { margin: .55rem 0 0; color: #66716e; font-size: .6rem; }
.task-control p i { display: inline-block; width: .55rem; height: .55rem; margin: 0 .25rem 0 .6rem; }
.task-control p i:first-child { margin-left: 0; }
.task-control .pass { background: #3b8778; }
.task-control .fail { background: #aa5435; }
.task-control .warn { background: #b68b42; }
.task-columns { display: grid; grid-template-columns: 1fr 1fr; gap: 1px; margin-top: 1rem; background: rgba(30,38,43,.15); border: 1px solid rgba(30,38,43,.15); }
.task-columns > article { min-width: 0; padding: 1rem; background: #f1ede3; }
.task-columns > article > header { display: flex; justify-content: space-between; gap: 1rem; color: #304349; font: 720 .58rem/1.2 var(--font-mono); }
.task-grid { display: grid; grid-template-columns: 1fr 1fr; gap: 1px; margin-top: .75rem; background: rgba(30,38,43,.12); }
.task-grid article { min-width: 0; padding: .75rem; background: #faf7ef; box-shadow: inset .25rem 0 #aa5435; }
.task-grid article.pass { box-shadow: inset .25rem 0 #3b8778; }
.task-grid article.warn { box-shadow: inset .25rem 0 #b68b42; }
.task-grid b,
.task-grid span,
.task-grid em { display: block; overflow-wrap: anywhere; }
.task-grid b { color: #34474c; font: 660 .53rem/1.3 var(--font-mono); }
.task-grid span { margin-top: .45rem; color: #263e43; font: 740 .58rem/1.2 var(--font-mono); }
.task-grid em { margin-top: .32rem; color: #737b77; font: .45rem/1.2 var(--font-mono); }
.task-summary { display: grid; grid-template-columns: 1fr 1fr; gap: 1rem; align-items: end; margin-top: .8rem; padding-top: .8rem; border-top: 1px solid rgba(30,38,43,.1); }
.task-summary b { display: block; margin-top: .35rem; color: #2f7266; font: 760 .82rem/1 var(--font-mono); }
.task-summary p { margin: 0; color: #6c7571; font-size: .57rem; line-height: 1.5; }
.sandbox-flow { display: grid; grid-template-columns: 1fr auto 1fr auto 1fr auto 1fr; gap: .55rem; align-items: center; margin-top: 1rem; }
.sandbox-flow article { min-height: 8.5rem; padding: .8rem; border: 1px solid rgba(30,38,43,.14); background: #eeeae0; }
.sandbox-flow article.active { color: white; background: #285249; }
.sandbox-flow > i { color: #a75534; }
.sandbox-flow span { color: #a65434; font: 720 .48rem/1.2 var(--font-mono); }
.sandbox-flow article.active span { color: #85c8bc; }
.sandbox-flow b { display: block; margin-top: .55rem; font: 730 .62rem/1.35 var(--font-mono); }
.sandbox-flow p { margin: .65rem 0 0; color: #69736f; font-size: .57rem; line-height: 1.5; }
.sandbox-flow article.active p { color: rgba(255,255,255,.75); }
.depth-controls { grid-template-columns: 1.25fr .85fr 1fr; }
.depth-chart { margin-top: 1rem; border: 1px solid rgba(30,38,43,.14); background: #fdfaf3; }
.depth-chart header { display: flex; justify-content: space-between; gap: 1rem; padding: .7rem .9rem; color: #dfe9e6; background: #27434a; font: 690 .55rem/1.2 var(--font-mono); }
.depth-chart svg { display: block; width: 100%; height: auto; }
.depth-chart svg text { fill: #78817d; font: 18px var(--font-mono); }
.depth-chart .chart-grid line { stroke: rgba(39,67,74,.14); stroke-width: 1; }
.depth-chart polyline { fill: none; stroke: #ac5736; stroke-width: 4; stroke-linecap: round; stroke-linejoin: round; }
.depth-chart circle { fill: #2f8071; stroke: #fff; stroke-width: 3; }
.router-chart polyline { stroke: #347b6e; }
.router-chart circle { fill: #ad5935; }
.depth-strip { display: grid; grid-template-columns: repeat(29, 1fr); gap: 2px; margin-top: .5rem; }
.depth-strip button { position: relative; display: flex; align-items: end; justify-content: center; min-width: 0; height: 3.7rem; padding: 0; overflow: hidden; color: #586562; border: 1px solid rgba(30,38,43,.1); background: #e4e0d6; cursor: pointer; }
.depth-strip button i { position: absolute; inset: auto 0 0; height: 4%; background: rgba(175,83,49,.7); }
.depth-strip button span { position: relative; z-index: 1; padding-bottom: .25rem; font: 680 .43rem/1 var(--font-mono); }
.depth-strip button.selected { color: white; border-color: #263f46; background: #263f46; }
.depth-strip button.selected i { background: #b66d48; }
.router-strip { grid-template-columns: repeat(26, 1fr); }
.router-strip button i { background: rgba(47,126,109,.72); }
.depth-reading { display: grid; grid-template-columns: repeat(5, 1fr); gap: 1px; margin-top: .8rem; background: rgba(30,38,43,.13); border: 1px solid rgba(30,38,43,.13); }
.depth-reading article { min-width: 0; padding: .8rem; background: #eeeae0; }
.depth-reading b { display: block; margin-top: .4rem; color: #243b41; font: 750 .68rem/1.25 var(--font-mono); overflow-wrap: anywhere; }
.depth-reading p { margin: .35rem 0 0; color: #6e7773; font-size: .54rem; line-height: 1.4; }
.depth-boundary { display: grid; grid-template-columns: 13rem 1fr; gap: 1rem; margin-top: 1rem; padding: .9rem; color: white; background: #44322e; }
.depth-boundary b { color: #e3a77c; font: 720 .58rem/1.3 var(--font-mono); }
.depth-boundary p { margin: 0; color: rgba(255,255,255,.74); font-size: .64rem; line-height: 1.55; }
.repro-proof { grid-template-columns: repeat(4, 1fr); }
.repro-proof article { background: #eeeae0; }
.repro-proof article.pass { background: rgba(54,128,108,.11); }
.artifact-links { display: flex; flex-wrap: wrap; gap: .5rem; margin-top: 1rem; }
.artifact-links a { padding: .55rem .7rem; color: #2d625b; border: 1px solid rgba(45,98,91,.25); background: rgba(45,98,91,.06); font: 680 .57rem/1.2 var(--font-mono); }
.completion-depth-lab figcaption { padding: .9rem 1.55rem; color: #75807c; border-top: 1px solid rgba(30,38,43,.13); background: #e8e4d9; font-size: .59rem; line-height: 1.5; }
.completion-depth-lab figcaption span { color: #a65031; font-weight: 750; }
.completion-depth-lab figcaption code { font-size: .55rem; overflow-wrap: anywhere; }
@media (max-width: 1040px) {
.cd-ledger { grid-template-columns: repeat(3,1fr); }
.cd-ledger article:nth-child(-n+3) { border-bottom: 1px solid rgba(30,38,43,.12); }
.incomplete-ledger > div { grid-template-columns: repeat(2,1fr); }
.depth-strip { overflow-x: auto; grid-template-columns: repeat(29, 2rem); }
.router-strip { grid-template-columns: repeat(26, 2rem); }
}
@media (max-width: 820px) {
.cd-head,
.cd-panel-lead,
.task-columns { grid-template-columns: 1fr; }
.cd-tabs { grid-template-columns: repeat(2,1fr); }
.budget-ladder { grid-template-columns: 1fr; }
.budget-arrow { display: none; }
.prefix-gate,
.repro-proof { grid-template-columns: 1fr; }
.depth-reading { grid-template-columns: repeat(2,1fr); }
.sandbox-flow { grid-template-columns: 1fr; }
.sandbox-flow > i { transform: rotate(90deg); text-align: center; }
}
@media (max-width: 620px) {
.cd-head,
.cd-panel { padding: 1rem; }
.cd-ledger { grid-template-columns: 1fr; }
.cd-ledger article { border-right: 0; border-bottom: 1px solid rgba(30,38,43,.12); }
.cd-tabs { display: flex; overflow-x: auto; }
.cd-tabs button { flex: 1 0 10.5rem; }
.condition-table { overflow-x: auto; }
.condition-table > header,
.condition-table > div { min-width: 38rem; }
.incomplete-ledger > header { display: block; }
.incomplete-ledger > header p { margin-top: .35rem; }
.incomplete-ledger > div,
.task-control,
.depth-controls,
.task-grid,
.depth-reading { grid-template-columns: 1fr; }
.task-summary,
.depth-boundary { grid-template-columns: 1fr; }
.depth-chart { overflow-x: auto; }
.depth-chart svg { min-width: 43rem; }
}
</style>
src/data/deepseek-v2-lite-chat-completion-512-eval.json
+3583
View File
File diff suppressed because it is too large Load Diff
src/data/deepseek-v2-lite-chat-completion-512-repro-1pd.json
+9568
View File
File diff suppressed because it is too large Load Diff
src/data/deepseek-v2-lite-chat-completion-512.json
+36640
View File
File diff suppressed because it is too large Load Diff
src/data/deepseek-v2-lite-chat-completion-depth-compact.json
+28492
View File
File diff suppressed because it is too large Load Diff
src/data/deepseek-v2-lite-chat-full-depth-repro-1pd.json
+288050
View File
File diff suppressed because it is too large Load Diff
src/data/deepseek-v2-lite-chat-full-depth.json
+1136822
View File
File diff suppressed because it is too large Load Diff
src/pages/deepseek/index.astro
+23 -8
View File
@@ -4,6 +4,7 @@ import DeepSeekLineage from "@/components/DeepSeekLineage.astro";
import DeepSeekLab from "@/components/DeepSeekLab.astro";
import DeepSeekArtifactLab from "@/components/DeepSeekArtifactLab.astro";
import DeepSeekBehaviorLab from "@/components/DeepSeekBehaviorLab.astro";
import DeepSeekCompletionDepthLab from "@/components/DeepSeekCompletionDepthLab.astro";
import { deepseekBranches, deepseekLedgers, deepseekPaperChain, deepseekWaves } from "@/data/deepseek";
const toc = [
@@ -31,21 +32,22 @@ const toc = [
["21", "lab", "四联交互实验"],
["22", "artifact", "真实权重执行"],
["23", "behavior", "Chat：最终生成行为"],
["24", "branches", "别漏掉旁支"],
["25", "audit", "事实、推导与教学模型"],
["24", "completion-depth", "Chat：完成度与全深度"],
["25", "branches", "别漏掉旁支"],
["26", "audit", "事实、推导与教学模型"],
["↳", "papers", "六十节点阅读链"],
];
---
<BaseLayout
title="DeepSeek 技术谱系与真实权重深读：从 Dense、MoE、MLA 到 R1 与 V4"
description="用二十四张问题账、十次技术转向、十八个交互实验、真实 V2-Lite Base / Chat 权重、公开语料路由区间、官方模板、消息历史、等长 filler、特殊词元家族、完整角色块与最终生成行为控制、吸收式缓存 trace 和六十个一手节点，完整理解 DeepSeek 的 MoE、MLA、FP8、DualPipe、GRPO、R1、V3.2 与 V4。"
description="用二十四张问题账、十次技术转向、十九个交互实验、真实 V2-Lite Base / Chat 权重、512-token 完成度评测、29 阶段隐藏状态与 26 层 MoE 路由追踪、吸收式缓存 trace 和六十个一手节点，完整理解 DeepSeek 的 MoE、MLA、FP8、DualPipe、GRPO、R1、V3.2 与 V4。"
section="deepseek"
>
<header class="page-hero deepseek-hero">
<div class="page-hero-inner">
<div>
<p class="eyebrow"><span>SPOTLIGHT / DEEPSEEK · ROUND 04</span> ROUTING × CHAT OUTPUT × REAL WEIGHTS</p>
<p class="eyebrow"><span>SPOTLIGHT / DEEPSEEK · ROUND 05</span> COMPLETION × FULL DEPTH × REAL WEIGHTS</p>
<h1>不要背模型名<br />要看懂每次为什么转向</h1>
<p class="lead">
这不是七篇报告的摘要，而是一套可追问、可计算、可反驳的技术谱系：
@@ -57,9 +59,9 @@ const toc = [
<div><dt>SPAN</dt><dd>2024.01 → 2026.06</dd></div>
<div><dt>LEDGERS</dt><dd>24 张问题账</dd></div>
<div><dt>LINEAGE</dt><dd>10 次技术转向</dd></div>
<div><dt>LABS</dt><dd>18 个可操作实验</dd></div>
<div><dt>LABS</dt><dd>19 个可操作实验</dd></div>
<div><dt>EVIDENCE</dt><dd>60 个一手 / 官方节点</dd></div>
<div><dt>STATUS</dt><dd>三轮 · 真实权重执行</dd></div>
<div><dt>STATUS</dt><dd>五轮 · 全 27 层执行</dd></div>
</dl>
</div>
</header>
@@ -795,8 +797,21 @@ const toc = [
<DeepSeekBehaviorLab />
</section>
<section class="article-section" id="completion-depth">
<p class="eyebrow"><span>24</span> COMPLETION IS NOT CORRECTNESS</p>
<h2>把 128-token 的截断账补齐，再沿完整 27 层看差异怎样传播</h2>
<p class="lede">
上一轮证明固定 Chat checkpoint 的 greedy 输出会分叉，却有 97 / 128 格在 128-token
上限处停止。这一轮对全部 128 格统一重跑 512-token 预算，用官方 GSM8K gold 与
HumanEval tests 分开记录完成、可评测和正确；同时在相同输入上执行 prompt-only
全深度 forward，追踪 29 个隐藏状态阶段、26 个 MoE gate 与 1,918,176 次 top-6
目标路由决定。隐藏状态、路由与任务结果仍是三类证据，不互相冒充因果解释。
</p>
<DeepSeekCompletionDepthLab />
</section>
<section class="article-section" id="branches">
<p class="eyebrow"><span>24</span> THE MAIN LINE IS NOT THE WHOLE TREE</p>
<p class="eyebrow"><span>25</span> THE MAIN LINE IS NOT THE WHOLE TREE</p>
<h2>如果只读 V2 → V3 → R1 → V4，会漏掉五条反过来影响主线的旁支</h2>
<div class="branch-grid">
{deepseekBranches.map(([name, line, text, url]) => (
@@ -816,7 +831,7 @@ const toc = [
</section>
<section class="article-section" id="audit">
<p class="eyebrow"><span>25</span> EVIDENCE AUDIT</p>
<p class="eyebrow"><span>26</span> EVIDENCE AUDIT</p>
<h2>同一张页面里有三种知识，它们的语气必须不同</h2>
<div class="audit-grid">
<article class="reported">
src/pages/index.astro
+5 -5
View File
@@ -145,18 +145,18 @@ const paths = [
</a>
<a class="release-card deepseek-release" href="/deepseek/">
<div>
<p class="eyebrow"><span>NEW / DEEPSEEK ROUND 04</span> LINEAGE · REAL WEIGHTS · ROUTES · GENERATION</p>
<p class="eyebrow"><span>NEW / DEEPSEEK ROUND 05</span> COMPLETION · TASK TESTS · FULL DEPTH</p>
<h2>从 Dense 到百万上下文：每次创新都在偿还上一代最贵的一张账</h2>
<p>
用二十四张问题账和十次技术转向走完 Dense→V4，再把 Base 路由证据接到官方
V2-Lite-Chat 的 31.4 GB 完整 BF16 权重：16 个公开来源、8 种边界条件生成
128 个输出，并把 31 个自然 EOS 与 97 个长度截断分开解释。
用二十四张问题账和十次技术转向走完 Dense→V4，再把官方 V2-Lite-Chat 的
128 个输出统一延长到 512-token：121 个自然 EOS、Math / Code 真实 evaluator；
同时沿 29 个隐藏阶段与 26 个 MoE gate 追踪 1,918,176 次目标路由决定。
</p>
</div>
<dl>
<div><dt>LINEAGE</dt><dd>1991 → 2026 · 10 次转向</dd></div>
<div><dt>NODES</dt><dd>60 个一手 / 官方节点</dd></div>
<div><dt>LAB</dt><dd>4 公式 · 13 Base 工件 · 1 Chat 行为</dd></div>
<div><dt>LAB</dt><dd>19 · Base / Chat / full depth</dd></div>
</dl>
<span class="release-arrow" aria-hidden="true">进入 DeepSeek 完整技术谱系 →</span>
</a>
src/pages/progress/index.astro
+8 -4
View File
@@ -15,7 +15,7 @@ const workstreams = [
{ label: "表示、位置与残差高速公路", value: 81, next: "加入真实 hidden-state / norm traces、长上下文位置外推复现与更多深层稳定性消融" },
{ label: "Scaling Laws", value: 74, next: "加入真实拟合复现、置信区间与更多模型族对照" },
{ label: "数据工程与预训练配方", value: 73, next: "逐图精读 FineWeb / DCLM，加入真实去重与 mixture traces" },
{ label: "DeepSeek 专题", value: 98, next: "completion-aware 生成评测、完整 27 层与固定 batch content，再推进 SM90 FlashMLA、FP8/pipeline 与 R1-like RL" },
{ label: "DeepSeek 专题", value: 99, next: "扩大 completion/task 样本、sampling robustness 与干预式 mediation，再推进 SM90 FlashMLA、FP8/pipeline 与 R1-like RL" },
{ label: "指令微调与人类偏好", value: 75, next: "加入真实偏好分歧样本、RM 长度偏置与 PPO/DPO 小模型复现" },
{ label: "推理与测试时扩展", value: 76, next: "真实模型采样曲线、PRM 案例与逐篇图表精读" },
{ label: "工具使用与长程 Agent", value: 74, next: "补真实环境 traces、cross-harness 对照、Agent RL 训练曲线与安全案例" },
@@ -97,12 +97,12 @@ const workstreams = [
<article><span>✓</span><h3>K3 报告已结构化拆解</h3><p>47 页报告目录、151 条参考来源和架构/后训练/系统主线已经提取。</p></article>
<article><span>✓</span><h3>17 专题知识图</h3><p>从语言模型基础到评测安全，包含先修依赖和三条贯穿案例。</p></article>
<article><span>✓</span><h3>编辑式网站系统</h3><p>响应式导航、章节模板、侧栏、进度、论文链和证据提示组件。</p></article>
<article><span>✓</span><h3>八十五个原创交互视图</h3><p>K3 三轴图、八联报告实验与四联开放工件实验，DeepSeek 四联公式实验、十三联 Base 工件实验与一联完整 Chat 行为实验，以及语言模型前史、Transformer、表示深度、长上下文、MoE、推理、Agent、多模态、训练系统、推理服务、Scaling、数据工程、数值、Alignment 与评测安全专题。</p></article>
<article><span>✓</span><h3>八十六个原创交互视图</h3><p>K3 三轴图、八联报告实验与四联开放工件实验，DeepSeek 四联公式实验、十三联 Base 工件实验、Chat 行为与 completion/full-depth 两轮实验，以及语言模型前史、Transformer、表示深度、长上下文、MoE、推理、Agent、多模态、训练系统、推理服务、Scaling、数据工程、数值、Alignment 与评测安全专题。</p></article>
<article><span>✓</span><h3>十七篇首版长文</h3><p>K3、语言模型前史、Transformer、表示/位置/残差、DeepSeek、Scaling、数据工程、长上下文、MoE、后训练、推理、Agent、原生多模态、训练系统、推理服务、数值优化与评测安全专题。</p></article>
<article><span>✓</span><h3>语言模型前史深度专题</h3><p>八张独立问题账、33 个正式节点、20 段长文与概率—向量—记忆—对齐四联实验。</p></article>
<article><span>✓</span><h3>Transformer 深度专题</h3><p>十张独立问题账、40 个正式节点、21 段正文与 QKV—Mask—多头位置—Block 成本四联实验。</p></article>
<article><span>✓</span><h3>表示、位置与残差高速公路深度专题</h3><p>二十张问题账、66 个一手节点、DeepSeek/Kimi 双谱系，以及 Token—位置—Norm—Residual/FFN 四联实验。</p></article>
<article><span>✓</span><h3>DeepSeek 四轮真实权重里程碑</h3><p>在 Base 路由与缓存实证上，新增官方 V2-Lite-Chat 的 31.4 GB 完整 BF16 生成：16 个公开来源 × 8 条件得到 128 个输出，31 个自然 EOS、97 个长度截断；独立复跑的 32 / 32 token 序列 exact。逐来源双输出、十边分歧、GPU/CPU offload 与证据边界共同组成第十八个实验，不把生成差异越界写成能力。</p></article>
<article><span>✓</span><h3>DeepSeek 五轮真实权重里程碑</h3><p>统一 512-token 预算让自然 EOS 从 31 / 128 增至 121 / 128；GSM8K strict exact 23 / 32、HumanEval 官方 tests pass 24 / 32，并保留四任务/域的样本边界。相同 Chat checkpoint 再执行 29-stage hidden 与 26-gate route trace；1,856 个 hidden hashes、1,664 个 route hashes 和 1,664 个 weight hashes 在新进程子集复跑中全部 exact。</p></article>
<article><span>✓</span><h3>Kimi K3 技术报告二轮深读</h3><p>三十二张问题账、Figure 1–16 / Table 1–5 审计、100 节点阅读链，以及 Delta—Decay—AttnRes—LatentMoE—SiTU—QB—MOPD—Cache 八联实验。</p></article>
<article><span>✓</span><h3>Kimi K3 三轮开放工件里程碑</h3><p>固定官方 revisions，审计 96 个 shards、497,220 个 tensor entries 与真实 KDA / MLA / MoE / MoonViT shapes；四联实验分开显示层型、tensor anatomy、参数范围和复现边界。</p></article>
<article><span>✓</span><h3>FlashKDA RTX 5090 执行闸门</h3><p>隔离 CUDA 13.0 / glibc 2.39 编译 sm_120a wheel；6/6 官方参考逐元素相等，并完成 fixed / varlen、三种 state mode 的 1,800 个 CUDA Event samples。</p></article>
@@ -134,7 +134,7 @@ const workstreams = [
<div class="queue-table">
<div class="head"><b>优先级</b><b>专题</b><b>本轮交付</b><b>完成闸门</b></div>
<div><span>P0</span><strong>K3 三轮</strong><p>开放权重 traces → FlashKDA / AttnRes / MoE 真实行为 → Figure 1–16 数值重绘与独立复现</p><em>运行证据 + 逐图复现</em></div>
<div><span>P0</span><strong>DeepSeek 四轮</strong><p>completion-aware 行为评测 → 完整 27 层与固定 batch content → SM90 FlashMLA / FP8 / pipeline traces → R1-like RL 小模型复现</p><em>运行证据 + 独立复现</em></div>
<div><span>P0</span><strong>DeepSeek 五轮后续</strong><p>扩大任务与语言 source → sampling robustness → 干预式 mediation → SM90 FlashMLA / FP8 / pipeline traces → R1-like RL 小模型复现</p><em>运行证据 + 独立复现</em></div>
<div><span>P0</span><strong>Transformer 二轮</strong><p>多头电路逐图 → Pre/Post-LN 真实 traces → Flash/KV 配置与 kernel 对照</p><em>逐图笔记 + 实测边界</em></div>
<div><span>P0</span><strong>表示、位置与残差二轮</strong><p>真实 hidden-state / norm traces → 长上下文位置外推 → mHC / AttnRes 深层稳定性消融</p><em>可复现实验 + 逐图笔记</em></div>
<div><span>P0</span><strong>语言模型前史二轮</strong><p>Kneser–Ney / LSTM / Bahdanau 逐图 → 真实小语料复现 → tokenizer 公平性</p><em>可复现实验 + 逐图笔记</em></div>
@@ -229,6 +229,10 @@ const workstreams = [
<div><time>2026-07-29</time><b>Chat、生成行为与能力永久分层</b><p>完整官方 Chat 权重可以支撑真实生成；成对输出分歧只证明干预传播，没有 evaluator 与足够 completion 就不升级成能力判断。</p></div>
<div><time>2026-07-29</time><b>completion 是生成实验的首要审计字段</b><p>31 / 128 自然 EOS 与 97 / 128 长度截断同时显示；截断答案不冒充完整回答。</p></div>
<div><time>2026-07-29</time><b>offload 拓扑进入复现合同</b><p>31.4 GB BF16 权重按 GPU 25 层、CPU 2 层 + norm / lm_head 执行；设备切分不被写成模型结构。</p></div>
<div><time>2026-07-29</time><b>更长预算统一重跑全部八格</b><p>不选择性续写 97 个截断格；128→512 的 prompt hash 与前 128 generated tokens 必须全 exact。</p></div>
<div><time>2026-07-29</time><b>停止、终点、可评测与正确分四张账</b><p>自然 EOS 不等于答对；fallback 不冒充 strict completion；HumanEval tests pass 不冒充代码安全。</p></div>
<div><time>2026-07-29</time><b>全深度比较只保留 exact interior tokens</b><p>1,537 个 content tokens / condition 在八格中 ID exact；56 个跨字符边界 token 排除，不拿不同 token 比隐藏状态。</p></div>
<div><time>2026-07-29</time><b>表示与路由分叉不是中介因果</b><p>29-stage hidden 与 26-gate route 曲线描述传播；没有干预式 mediation 前不解释输出或能力因果。</p></div>
</div>
</section>