正在加载视频...
视频加载失败
llm.c by Hand✍️ C programming + matrix multiplication by hand This combination is perhaps as low as we can get to explain how the Transformer works. Special thanks to Andrej Karpathy for encouraging early feedback and tetsuo //: 👾 for helping me understand the pragma magic. I hope this... show more
11 条评论

@karpathy @7etsuo Awesome! Looking forward to an llm.c Attention episode

@karpathy @7etsuo This is a great suggestion! Thanks!

@karpathy @7etsuo Is there a way to load a single layer of a LLM (in example Llama3-70B) and process it layer by layer so it fits on a normal PC memory ? Could you explain how to do it ?

@karpathy @7etsuo It is possible. But it would be quite slow. To generate each token, the model has to evaluate every one of the hundreds of layers. Say loading each layer takes 1 second. It would take 100 seconds to load 100 layers for one token. Then you multiple that by 1000 tokens. Very slow.

@karpathy @7etsuo Goated acc

@karpathy @7etsuo Amazing 🔥

@karpathy @7etsuo 🔥

@karpathy @7etsuo This is awesome

@karpathy @7etsuo Is this also available elsewhere online?

@karpathy @7etsuo Can these be made into the notebooks!? That would be awesome.

@karpathy @7etsuo I am waiting for a notebook ninja to step up to help.😄

!["I've been told by multiple sources that we can expect [Joe Biden] to make his announcement as early as the weekend, perhaps next week, and to clear the way for Kamala Harris and perhaps others to compete for the nomination." — Mark Halperin, political analyst Rob Finnerty](https://image.24vids.com/tw-1814265937966637084/media/GS2Qy_rbMAAxygH.jpg)
