TR

Transformer

概念
本站收录 10 集 · 5 条金句 · 关联 10 个

集里怎么说它

① 提到它的金句

5 条

如果 Transformer 是有利可图的,如果你可以花费更多的努力和资源来扩大 Transformer 以在下一个季度获胜,那么很难把大量的注意力和精力投入到可能在一两年内更好或重新定义该领域的事情上。
If Transformer is profitable and if you can spend more efforts and more resources scaling Transformer to win in the next quarter, it’s very hard to put at least a lot of attention and a lot of energy to work on something that will maybe better or maybe will redefine the field in a year or two.
—— Jerry Tworek · [13:28]

指向原始笔记的链接

目前的机制相当糟糕,如果你把它留给世界,我恐怕我们会花更长的时间才能替换 Transformer。
The current mechanisms are quite poor and it will if if you leave it to the world I am afraid that it will take us like a much longer time horizon before we replace the transformer
—— 嘉宾 · [18:15]

指向原始笔记的链接

所有这些建立在对数据和学习直觉之上的分析工作,造就了我们如今拥有的模型——相比 2017 年的 Transformer,它就像一艘忒修斯之船。
All of this analysis work built on intuitions about data and learning led to the model that we have now, which is like a ship of Theseus compared to the 2017 Transformer.
—— Chris Potts · [15:29]

指向原始笔记的链接

只要我们还在使用基于 transformer 的 LLM,这就是它们工作原理的数学本质,使用更少的上下文你就会得到更好的质量。
As long as we’re using transformer-based LLMs, that’s just like the math of how they work, and you will get better quality if you use less context.
—— Dex Horthy · [52:08]

指向原始笔记的链接

所以我想说,NVIDIA GPU 在 transformer 模型的实际解码前向传递中,平均只获得 30% 到 40% 的内存带宽利用率。
So while NVIDIA GPUs, I would say, on average are getting between 30 and 40 percent memory bandwidth utilization in the actual decode forward pass of a transformer model
—— Thomas Somers · [34:12]

指向原始笔记的链接

② 出现在这些集

10 集

③ 关联

点进去有真内容 —— 本页主要出口

智能体 · OpenAI · Anthropic · 推理 · Copilot · LLM · 预训练 · Claude Code · AGI · 强化学习