74 Commits

Author SHA1 Message Date
ff0789cdac feedback readme 2021-02-01 10:44:56 +05:30
7ec9fdc3b4 📚 switch readme 2021-02-01 10:35:54 +05:30
88d0f89ef5 ✍️ english 2021-02-01 07:33:01 +05:30
5cd2b8701b ✍️ mha english 2021-02-01 07:28:33 +05:30
9b09a5f3d2 pytorch link 2021-01-30 13:38:15 +05:30
3161c23592 typo 2021-01-29 15:15:44 +05:30
a0fa963c60 raw string fix 2021-01-29 14:46:44 +05:30
2a26ecaaa1 📚 feedback transformer notes 2021-01-29 14:34:04 +05:30
2f1918f6db feedback transformer update 2021-01-29 10:28:58 +05:30
93355c0674 urls 2021-01-26 17:22:15 +05:30
fe161514cc experiment notebook 2021-01-26 17:00:47 +05:30
abe5caba6f 📚 glu variants 2021-01-26 16:54:23 +05:30
20d2e27a3c 📚 ffn notes 2021-01-25 22:09:11 +05:30
d6ce459283 glu variants simple experiment 2021-01-25 17:04:51 +05:30
1efd55e2a7 GLU variants 2021-01-25 10:16:36 +05:30
75069d83e3 ffn glu variants configs & 🐛 gated ffn 2021-01-25 09:44:38 +05:30
0bf8951258 FFN ready for GLU 2021-01-24 09:31:53 +05:30
559a5e8b63 cleanup 2021-01-24 09:16:04 +05:30
137ab59eaf english 2021-01-24 08:08:09 +05:30
596e554330 link switch transformer 2021-01-21 09:52:30 +05:30
555862a8fe notebook 2021-01-21 09:40:46 +05:30
9a50322211 📚 switch transformer notes 2021-01-20 10:58:57 +05:30
278d18c73a Merge branch 'master' of github.com:lab-ml/labml_nn
merge
2021-01-20 10:36:56 +05:30
35e2bc6c96 notes 2021-01-20 10:36:51 +05:30
ec1cb8b27b shuffle 2021-01-20 10:19:22 +05:30
5d174f3a7c 📚 switch transformer notes 2021-01-20 10:14:21 +05:30
e3e321a5a9 switch transformer 2021-01-20 09:18:35 +05:30
ec45cd9437 typo 2021-01-14 10:22:01 +05:30
a94ed927aa gpt links 2021-01-14 10:20:21 +05:30
2cf6e7a079 colab notebook 2021-01-14 10:18:27 +05:30
e367505720 feedback experiment fix 2021-01-14 10:02:18 +05:30
55ec434132 gpt notes 2021-01-14 09:38:16 +05:30
2927aa217b gpt notes 2021-01-14 09:37:12 +05:30
4c769128cb autoregression trainer notes 2021-01-14 08:46:41 +05:30
fbb1026164 weight decouple fix 2021-01-13 20:33:25 +05:30
774a72e0bf gpt 2021-01-13 12:54:43 +05:30
0de6605c80 experiment notebook 2021-01-10 12:19:18 +05:30
9102883e1f transpose with \top 2021-01-10 12:16:50 +05:30
8ee70da198 feedback link 2021-01-10 11:52:08 +05:30
3ede1c3460 fix 2021-01-10 11:34:28 +05:30
1dc4ff825f feedback transformer notes 2021-01-10 10:22:46 +05:30
5874106161 feedback rtansformer notes 2021-01-09 21:06:41 +05:30
fa5805f275 relative mha 2021-01-09 10:52:49 +05:30
809a54d6aa relative attention notes 2021-01-09 10:41:25 +05:30
9f4b494bf2 feedback transformer 2021-01-09 07:28:25 +05:30
dfefde657b no loss smoothing 2021-01-07 12:02:19 +05:30
52d5b5fbf6 auto regression common exp 2020-12-27 07:35:35 +05:30
799a62a4fc underset fix 2020-12-21 21:33:55 +05:30
625e250351 fix \u 2020-12-21 08:54:00 +05:30
ac77ce006a mha explanation 2020-12-18 20:58:56 +05:30