跨国深谈

微调 (fine tune)

Properties1
aliasesfine tune, fine-tuning, fine-tuned

30分钟阅读

跨国深谈← 返回←微调 (fine tune)
微调

微调 (fine tune)

概念 · 又名 fine tune / fine-tuning / fine-tuned
本站收录 38 集 · 10 条金句 · 关联 10 个

集里怎么说它

① 提到它的金句

10 条

但我认为你需要拥有自己的微调栈，我不会把微调相关的东西交给别人。
But I think you need to own your fine-tuning stack and I would not give the fine-tuning stuff to somebody else.
—— Mustafa Suleyman · [18:29]

指向原始笔记的链接

你知道,如果你看今天任何美国开源模型,它们都在使用中国模型作为老师,或在某种程度上作为微调过程的一部分。
you know, if you look at any American open source model today, they are using Chinese models as a teacher or in a way as a part of the fine tuning process.
—— Sriram Krishnan · [15:25]

指向原始笔记的链接

所以当我们微调更小、更笨的模型时,它们只是没那么通用,但在我们想要它们做的特定任务上,它们实际上优于那些大型、聪明、最先进的模型。
So when we fine-tune smaller, dumber models, it’s that they’re just not as general purpose, but on the specific task we want them to do, they actually outperform the large, smart, state-of-the-art models.
—— Jesse Zhang · [05:34]

指向原始笔记的链接

我们还发现，如果在神经网络中加入这些波，你会非常自然地运行在混沌边缘，而不必微调系统去凑到那里。
And we found that if you include these waves in your neural network, you very naturally operate in this regime edge of chaos, and you don’t have to fine-tune the system to be there.
—— Max Welling · [52:58]

指向原始笔记的链接

我们白天推理,晚上微调,明天我们会比今天更聪明一点。
We infer during the day, we fine tune at night, and tomorrow we’ll be a little bit smarter than we were today.
—— Renen Hallak · [06:29]

指向原始笔记的链接

所以在稳态下，一个更大的语言模型大概总是会胜过更小的模型，但小模型用 LoRA 微调足够便宜，以至于在足够窄的语料库上，你也可以非常快地微调一个小模型，让它在个性化语料库上变得更好，并为特定任务对模型进行个性化。
And so a larger language model will probably always outperform a smaller one at steady state, but the smaller ones are cheap enough to fine tune using LoRa that on narrow enough corpuses, you can very quickly also fine tune a small model on a narrow corpus and make it better at individualized corpuses and personalize the model for specific tasks.
—— Hamad Bashir · [32:22]

指向原始笔记的链接

从边际信息增益的角度来看,这是用于微调下一版智能体的最佳数据类型。
From a marginal information gain standpoint, that’s the best type of data to collect to fine tune the next iteration of the agent.
—— Jonathan · [32:03]

指向原始笔记的链接

嗯,因为当你用支持工单微调时,产品目录已经泄漏进权重里了。
Well, the product catalog leaked into the weights when you fine-tuned it on your support tickets.
—— Anant Srivastava · [04:23]

指向原始笔记的链接

通常,你会微调你的模型去学习反射,而不是事实。
You’d fine-tune your model to learn reflexes, not facts, typically.
—— Anant Srivastava · [09:43]

指向原始笔记的链接

微调的诊断标准是:信息是否已经停止变化?
Fine-tuning is, has the information stopped changing?
—— Anant Srivastava · [16:18]

指向原始笔记的链接

② 出现在这些集

38 集

③ 关联

点进去有真内容 —— 本页主要出口

智能体 · 推理 · OpenAI · Anthropic · NVIDIA · 蒸馏 · 后训练 · 开源模型 · 评估 · LLM

反向链接