llvm YouTube動画>1本

ビルドに2時間かかる

LLVM IR出力すればPythonとかでもコンパイラ書けるのすごいと思う

Python + Larkで構文解析器して、llvmliteでLLVM IRを吐き出せば、誰でもコンパイラ作れる時代

うちなんか、llvm -> lld -> compiler-rt -> clang+extra-tools までで5時間だぞ()

おまえら、stand-alone build してないの?

Let's reproduce GPT-2 (124M) - YouTube



Andrej Karpathy

2024/06/10
We reproduce the GPT-2 (124M) from scratch. This video covers the whole process: First we build the GPT-2 network, then we optimize its training to be really fast, then we set up the training run following the GPT-2 and GPT-3 paper and their hyperparameters, then we hit run, and come back the next morning to see our results, and enjoy some amusing model generations. Keep in mind that in some places this video builds on the knowledge from earlier videos in the Zero to Hero Playlist (see my channel). You could also see this video as building my nanoGPT repo, which by the end is about 90% similar.

加熱するLLM開発競争に冷や水、オープンモデルの組み合わせだけでGPT-4o越えの事実 ? WirelessWire News
https://wirelesswire.jp/2024/06/86709/