[WIP] Recurrent MQA Transformer — depth recurrence + weight tying (nidhilak-Aquarius)#29
Closed
nidhilak-Aquarius wants to merge 5 commits intoopenai:mainfrom
Closed
[WIP] Recurrent MQA Transformer — depth recurrence + weight tying (nidhilak-Aquarius)#29nidhilak-Aquarius wants to merge 5 commits intoopenai:mainfrom
nidhilak-Aquarius wants to merge 5 commits intoopenai:mainfrom