Files
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
ai-agent-book 精选快照(<2MB 代码与文档,来自 github.com/bojieli/ai-agent-book)
2026-08-20 13:12:50 +00:00

68 lines
5.5 KiB
JSON
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"signature": "ca63c262f538d79e6aa5057385782315042b464816023e0f181c47dcb0583655",
"parsed": {
"narration": "前面我们从机制上讲清了自注意力怎么算,这一页就来看它真正学到的效果。请大家看屏幕中间这张可视化图:这是编码器第五层的自注意力,句子中词与词之间的连线代表注意力强弱。重点请关注动词 making——它没有只盯着相邻的词,而是把注意力投向了距离很远的句首,指向它真正的依赖对象。这就是标题说的长距离依赖:传统循环网络要一步步传递信息,距离一远信号就衰减,而自注意力一步到位,直接建立连接,代价和距离无关。这也回应了我们前面反复强调的并行化与全局感受野。下一页,我们再看一个更有挑战性的指代消歧例子。",
"visual_references": [
"标题 Attention Visualization: Long-Distance Dependencies",
"屏幕中间的注意力连线可视化图",
"图中动词 making 的注意力分布",
"图注:encoder self-attention in layer 5"
]
},
"receipt": {
"provider": "Moonshot",
"request": {
"model": "kimi-k3",
"messages": [
{
"role": "user",
"content": "你是一位严谨而自然的中文技术讲师,正在讲解论文 Attention Is All You Need。\n这是第 10/12 页。下面给出该页真实 Slidev 源码:\n<slide>\n## Attention Visualization: Long-Distance Dependencies\n\n<img src=\"/paper_figure_3_long_distance.png\" class=\"h-70 mx-auto\" />\n\n*Encoder self-attention in layer 5 showing attention to distant dependency of the verb \"making\"*\n</slide>\n请写一段 180–240 个中文字符左右的口语讲解。必须满足:\n1. 用引导性叙事解释“为什么”和“它与前后页的关系”,不能逐条照读幻灯片;\n2. 明确指向当前屏幕上的可见元素(标题、公式、表格、数值或图片);有图片/表格/公式时必须说出观众该看哪里;\n3. 不虚构源码中没有的数值或结论;开头/结尾与页序匹配;\n4. 只返回 JSON{\"narration\":\"...\",\"visual_references\":[\"...\"]}。\n"
}
],
"temperature": 1,
"max_tokens": 1200,
"response_format": {
"type": "json_object"
}
},
"response": {
"id": "chatcmpl-6a6acf696ff171b3d8c3411c",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "{\"narration\":\"前面我们从机制上讲清了自注意力怎么算,这一页就来看它真正学到的效果。请大家看屏幕中间这张可视化图:这是编码器第五层的自注意力,句子中词与词之间的连线代表注意力强弱。重点请关注动词 making——它没有只盯着相邻的词,而是把注意力投向了距离很远的句首,指向它真正的依赖对象。这就是标题说的长距离依赖:传统循环网络要一步步传递信息,距离一远信号就衰减,而自注意力一步到位,直接建立连接,代价和距离无关。这也回应了我们前面反复强调的并行化与全局感受野。下一页,我们再看一个更有挑战性的指代消歧例子。\",\"visual_references\":[\"标题 Attention Visualization: Long-Distance Dependencies\",\"屏幕中间的注意力连线可视化图\",\"图中动词 making 的注意力分布\",\"图注:encoder self-attention in layer 5\"]}",
"refusal": null,
"role": "assistant",
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": null,
"reasoning_content": "This is page 10 of 12. Need 180-240 Chinese characters narration, JSON output only. The slide shows attention visualization, encoder self-attention layer 5, long-distance dependency of verb \"making\". Must reference visible image. Connect to previous pages (multi-head attention) and next (remaining visualizations/conclusion). Don't fabricate numbers. Paper figure 3 shows the word \"making\" attending to distant words.\n\nWrite ~180-240 chars. Let me draft:\n\n\"前面我们从机制上讲了自注意力怎么算,现在看看它实际学到了什么。请大家看屏幕中间这张图:这是编码器第五层的自注意力可视化,一句话里每个词与其他词的连线,颜色越深代表注意力越强。重点看动词 making——它并没有只盯着旁边的词,而是把目光投向了句首远处的 it,也就是它真正的主语。这正是长距离依赖:传统 RNN 要一步步传信息,距离远了就容易丢,而自注意力一步直达。下一页我们再看另一个更难的指代例子。\"\n\nCount characters roughly: that's about 200 chars. Good. Visual references: 标题, 中间可视化图, making 的注意力连线, layer 5 caption.\n\nEnsure no fabricated numbers beyond \"第五层\" which is in slide. Good. JSON only."
}
}
],
"created": 1785384811,
"model": "kimi-k3",
"object": "chat.completion",
"service_tier": null,
"system_fingerprint": null,
"usage": {
"completion_tokens": 460,
"prompt_tokens": 346,
"total_tokens": 806,
"completion_tokens_details": {
"accepted_prediction_tokens": null,
"audio_tokens": null,
"reasoning_tokens": 262,
"rejected_prediction_tokens": null
},
"prompt_tokens_details": null
}
},
"elapsed_ms": 21099.258
}
}