liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
25 lines
5.3 KiB
XML
25 lines
5.3 KiB
XML
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 40 780 340" width="780" height="340" style="background:#ffffff">
|
||
<defs><marker id="ah" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#333333"/></marker><marker id="ah-light" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#999999"/></marker></defs>
|
||
|
||
<rect x="40" y="65" width="300" height="130" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="190" y="88" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">階段一：SFT 固化格式</text>
|
||
<text x="190" y="115" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">目標：輸出可解析（JSON/工具呼叫）</text>
|
||
<text x="190" y="137" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">資料：數千條高質量示範</text>
|
||
<text x="190" y="159" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">停止條件：格式穩定，能力初具</text>
|
||
<text x="190" y="181" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">⚠ 過度訓練 → 模型塌縮到訓練分佈</text>
|
||
<line x1="342" y1="130" x2="398" y2="130" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
||
<text x="370" y="115" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">格式</text>
|
||
<text x="370" y="135" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">穩定</text>
|
||
<rect x="400" y="65" width="340" height="130" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
|
||
<text x="570" y="88" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">階段二：RL 塑形策略</text>
|
||
<text x="570" y="115" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">目標：最大化任務獎勵（準確率/成功率）</text>
|
||
<text x="570" y="137" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">前提：輸出格式穩定 → 獎勵可計算</text>
|
||
<text x="570" y="159" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">突破：發現超越 SFT 示範的新策略</text>
|
||
<text x="570" y="181" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">✓ 格式穩定 + 策略泛化 = 部署就緒</text>
|
||
<rect x="40" y="220" width="700" height="70" rx="4" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
||
<text x="390" y="238" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">為什麼不能跳過 SFT 直接 RL？</text>
|
||
<text x="390" y="262" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">基礎模型輸出無結構 → 無法解析 JSON → 獎勵函式返回 NaN → 梯度全零 → 訓練完全失敗</text>
|
||
<text x="390" y="310" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">SFT 記憶分佈 → RL 泛化策略</text>
|
||
<text x="390" y="338" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">SFT: max Σ log P(y|x)（擬合訓練分佈） RL: max E[R(τ)]（最佳化任務目標）</text>
|
||
<text x="390" y="362" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">當"無論增加多少示範，新場景仍不佳"時 → 轉向 RL 的臨界點</text>
|
||
</svg> |
