Commit Graph

7 Commits

Author SHA1 Message Date
aidoge 883cda1a2c fix freq_cos, freq_sin serialize 2023-08-01 16:31:43 +08:00
aidoge 36bf904c18 Refactor freqs_cis into freqs_cos and freqs_sin, and remove complex64 for ONNX export compatibility 2023-07-26 14:23:25 +08:00
Andrej Karpathy f5650891d5 honestly at this point this is a lot more my nanogpt code than llama code 2023-07-25 23:57:03 +00:00
Andrej Karpathy 624cdfc76a add dropout support to model 2023-07-24 14:18:50 +00:00
Andrew Gu af3b5c0364 Register freqs_cis as non-persistent buffer 2023-07-24 03:18:20 +00:00
Andrej Karpathy 9414e7a45e tweaks and add a simple test 2023-07-23 14:52:08 +00:00
Andrej Karpathy 5b161abb9a somewhere ~20 hours later 2023-07-23 05:23:45 +00:00