81 Commits (88e921bf107ba6e5a67e1bdf61d1af056f23a60d)
 

Author SHA1 Message Date
BlinkDL 3b9005ea11 RWKV: now faster and less params 4 years ago
BlinkDL 546114c6a5 still use layernorm for everything 4 years ago
PENG Bo c68ea168b1
Update README.md 4 years ago
PENG Bo 73a63e175f
Update README.md 4 years ago
PENG Bo 2df321d3f4
Update README.md 4 years ago
PENG Bo 6e2ba61d95
Update README.md 4 years ago
PENG Bo cd9b352b45
Update README.md 4 years ago
PENG Bo d2b100c2ac
Update README.md 4 years ago
PENG Bo 8af6289d0c
Update README.md 4 years ago
BlinkDL fd098b1d2e small update 4 years ago
PENG Bo 3b01c8c3cf
Update README.md 4 years ago
BlinkDL 65eda0f915 no message 4 years ago
BlinkDL 3b60c5b266 add wandb, and rename variables 4 years ago
BlinkDL 440bebff1a fixed nan in large models 4 years ago
PENG Bo f80ff53595
Update README.md 4 years ago
BlinkDL 62e2cb06d6 fixing nan in large models 4 years ago
BlinkDL d699a69169 misc improvements 4 years ago
BlinkDL 6266f481da minor changes 4 years ago
PENG Bo 88297e7949
Update README.md 4 years ago
BlinkDL 89eab46e60 + info 4 years ago
BlinkDL e9fbd9bf70 remove layernorm -> better RWKV 4 years ago
BlinkDL 55405c57d0 better splitting of words 4 years ago
BlinkDL 01d6972f4f now works for word-level LM 4 years ago
PENG Bo 64fdb61056
Update README.md 4 years ago
PENG Bo 959115a7e6
Update README.md 4 years ago
BlinkDL 447eae5841 add MHA-plus model 4 years ago
PENG Bo bcd4adb781
Update README.md 4 years ago
PENG Bo 1035a7438e
Update README.md 4 years ago
PENG Bo 4c6db5607c
Update README.md 4 years ago
BlinkDL aa4e2a68f4 first commit 4 years ago
PENG Bo d21af78c97
Initial commit 4 years ago