Default Branch

master

eba36e8464 · Merge pull request #309 from ho2103/master · Updated 2023-06-22 08:24:17 -07:00

Branches

bias_test

2892858ce7 · attempt a non-biased model, per few papers that cite this as working well · Updated 2023-01-27 18:54:08 +00:00

101
0
Included
init_test

23a0bfac20 · try bring back mingpt init · Updated 2023-01-27 16:52:18 +00:00

103
0
Included
multi_node_ddp

684800dd87 · clarify that these should be run on two separate machines · Updated 2023-01-16 06:02:46 +00:00

126
0
Included
tie_weights

89da79eee1 · add note of caution for the produced warning, investigate later · Updated 2023-01-14 20:38:22 +00:00

131
0
Included
autocast_wip

8b2e622b27 · adjust the readme to reflect changes in the autocast branch · Updated 2023-01-08 19:40:46 +00:00

146
0
Included