Embedding/Chinese-Word-Vectors ? reverse-engineered prompt
Reverse engineered prompt
Build me a simple website for this Chinese word vectors project, so people can browse the available pretrained embeddings by corpus and by type, then download the one they want.
I want the page to clearly explain that the vectors are in plain text format, with dense and sparse options, and that there’s also a Chinese analogy dataset called CA8 plus an evaluation toolkit. Make it easy to see the different corpora, like encyclopedia, Wikipedia, news, Zhihu, Weibo, and literature, and to understand which ones are word only, word plus ngram, word plus character, or both.
Also add a small evaluation section where someone can upload or point to a vector file and run the included test sets or at least get guided instructions for evaluating it. Keep the design clean, mostly content focused, and make the downloads and README style info very easy to find. If you need to check current docs or best practices, look them up online.
Are you gonna build this?
make sure you review the code using coderabbit