ai-agent-book 精选快照（<2MB 代码与文档，来自 github.com/bojieli/ai-agent-book）
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
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
This commit is contained in:
@@ -0,0 +1,25 @@
|
||||
<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="16.5" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Этап 1: Форматирование для SFT</text>
|
||||
<text x="190" y="115" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="9" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Цель: получить разбираемый вывод (JSON/вызов инструмента)</text>
|
||||
<text x="176.3" y="137" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Данные: тысячи качественных демонстраций</text>
|
||||
<text x="190" y="159" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="7.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Условие остановки: формат стабилен, базовые возможности достигнуты</text>
|
||||
<text x="190" y="181" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="7.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">⚠ Переобучение → Модель коллапсирует к обучающему распределению</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">Формат</text>
|
||||
<text x="369.2" 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">Стабильный</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="17" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Этап 2: Стратегия формирования RL</text>
|
||||
<text x="570" y="115" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="8.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Цель: максимизировать вознаграждение за задачу (точность/доля успеха)</text>
|
||||
<text x="583.7" y="137" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="9.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Предпосылка: формат вывода стабилен → награда вычислима</text>
|
||||
<text x="570" y="159" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="9.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Прорыв: открытие новых стратегий за пределами демонстраций SFT</text>
|
||||
<text x="570" y="181" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="9.5" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">✓ Стабильный формат + Обобщение стратегии = Готово к внедрению</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">Почему нельзя пропустить SFT и сразу перейти к RL?</text>
|
||||
<text x="390" y="262" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="7.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Вывод базовой модели неструктурирован → JSON не парсится → Функция вознаграждения возвращает NaN → Градиенты все нулевые → Обучение полностью проваливается</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 запоминает распределение → RL обобщает стратегию</text>
|
||||
<text x="390" y="338" 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">SFT: max Σ log P(y|x) (подгонка под обучающее распределение) RL: max E[R(τ)] (оптимизация целевой задачи)</text>
|
||||
<text x="390" y="362" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Когда «сколько бы примеров ни добавляли, на новых сценариях результат остаётся плохим» → переломный момент для перехода к RL</text>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 6.4 KiB |
Reference in New Issue
Block a user