预训

预训练 (pre-training)

概念
本站收录 9 集 · 8 条金句 · 关联 10 个

集里怎么说它

① 提到它的金句

8 条

在这个中间过程中,既然每个人都有非常相似的预训练数据,那后训练就是如今他们做出大差异的地方。
where like post-trading, but middle course of this is more of everyone have very similar pre-training data, is that post-training is where they make a big difference nowadays.
—— Chip Huyen · [15:10]

指向原始笔记的链接

是的,我认为这是一个好问题,对开发者来说宽容的看法是,如果有一件事你真的不想搞乱,那就是预训练,因为它只是比你做的其他任何训练过程都要昂贵几个数量级。
Yeah, I think it’s a good question and the charitable take for developers is that if there’s one thing you really don’t want to mess with, it is pre-training because this is just orders of magnitude more expensive than every other training procedure that you do.
—— Adam Gleave · [74:22]

指向原始笔记的链接

过去做后训练是不值得的,因为模型通过预训练提升得太快,你做的任何后训练很快就会被下一个预训练模型吸收掉。
In the past, it wasn’t worth doing post-training because the models were improving so quickly from pre-training that any post-training you did quickly got absorbed by the next pre-trained model.
—— Gabe Pereyra · [06:04]

指向原始笔记的链接

并不清楚的是,用新架构和新范式预训练一个新模型的第一个周期,第一个周期就奏效是疯狂的。
It’s not clear that the first cycle of pre-training a new model with a new architecture and a new paradigm, the first cycle of that working is insane.
—— Justin Johnson · [22:32]

指向原始笔记的链接

据我们所知,我们是唯一做过稳健的数百万 token 预训练的人。
As far as we know, we are the only people to do robust multi-million token pre-training.
—— Alexander Whedon · [11:26]

指向原始笔记的链接

研究在很大程度上表明,你在后训练阶段创造价值的能力,受限于你所做过的预训练。
And so research has largely suggested that your ability to create value in the post-training phase is limited by the pre-training that you’ve done.
—— Alexander Whedon · [20:31]

指向原始笔记的链接

你的预训练模型已经知道答案,而你针对一个已经存在于预训练语料库中的答案做强化学习时,系统基本上可以伪造一些工作、得到正确答案,而你会强化这些策略。
Your pre-trained model already knows the answer, and you do reinforcement learning derived against an answer that was already in the pre-training corpus, that the system can basically fake some work, get to the right answer, and you reinforce those strategies.
—— Doj Chubuk · [39:47]

指向原始笔记的链接

它的预训练中没有任何机器人数据。
had zero robot data in its pre-training.
—— Pete Florence · [19:50]

指向原始笔记的链接

② 出现在这些集

9 集

③ 关联

点进去有真内容 —— 本页主要出口

后训练 · 智能体 · 推理 · Anthropic · 合成数据 · OpenAI · Meta · ChatGPT · Claude · Palantir