Parents:
Simple idea
Related Tags:
 
ExpandDescendants
4 Documents (Long List) 
Zeyuan Allen-Zhu sur X : " surprisingly, when pre-training good data (e.g., Wiki) together with "junks" (e.g., Common Crawl), LLM's capacity on good data may decrease by 20x times!"
Tags:
2024-04-10 About
Unsupervised text classification with word embeddings - Max Halford
Tags:
2020-10-05 About
Keywords2vec
Tags:
2019-02-09 About
Jeremy Howard on Twitter: "Such a ridiculously simple idea couldn't possibly work, could it? Or... could it? "
Tags:
2019-02-09 About
Properties