{"id":"1909.00015","title":"Adaptively Sparse Transformers","url":"https://codeofpaper.com/paper/1909.00015","arxiv_url":"https://arxiv.org/abs/1909.00015","published":"2019-08-30","code":"official","best":{"full_name":"deep-spin/entmax","url":"https://github.com/deep-spin/entmax","tier":"official","stars":473,"license":"MIT","framework":null,"language":"Python","last_commit":"2024-06-22T14:34:00"},"most_starred_community":null,"implementations":[{"full_name":"deep-spin/entmax","url":"https://github.com/deep-spin/entmax","tier":"official","stars":473,"license":"MIT","framework":null,"language":"Python","last_commit":"2024-06-22T14:34:00"}],"possible_matches":0}