Wavecoder – a CodeLLM with 6.7B params scoring just behind GPT4

36 点作者 fgfm超过 1 年前

1 comment

lxe超过 1 年前

A 6.7B model that's as good as GPT-4 is mostly due to overfitting in such a way that favors certain benchmarks.

评论 #39038213 未加载

评论 #39032557 未加载