{"id":"1910.05895","title":"Transformers without Tears: Improving the Normalization of Self-Attention","url":"https://codeofpaper.com/paper/1910.05895","arxiv_url":"https://arxiv.org/abs/1910.05895","published":"2019-10-14","code":"official","best":{"full_name":"tnq177/transformers_without_tears","url":"https://github.com/tnq177/transformers_without_tears","tier":"official","stars":133,"license":"MIT","framework":"PyTorch","language":"Python","last_commit":"2024-05-29T17:00:13"},"most_starred_community":null,"implementations":[{"full_name":"tnq177/transformers_without_tears","url":"https://github.com/tnq177/transformers_without_tears","tier":"official","stars":133,"license":"MIT","framework":"PyTorch","language":"Python","last_commit":"2024-05-29T17:00:13"}],"possible_matches":0}