MCPcopy Create free account

hub / github.com/KellerJordan/modded-nanogpt / functions

Functions2,320 in github.com/KellerJordan/modded-nanogpt

Methodworld_size
(self)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/distributor/gpu_tests/shampoo_hybrid_shard_distributor_test.py:67
Methodworld_size
(self)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/distributor/gpu_tests/shampoo_hybrid_shard_distributor_test.py:530
Methodworld_size
(self)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/distributor/gpu_tests/shampoo_fsdp_distributor_test.py:61
Methodworld_size
(self)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/distributor/gpu_tests/shampoo_fsdp_distributor_test.py:261
Methodworld_size
(self)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/distributor/gpu_tests/shampoo_fully_shard_lossless_distributor_test.py:79
Methodworld_size
(self)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/distributor/gpu_tests/shampoo_fully_shard_lossless_distributor_test.py:309
Methodworld_size
(self)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/distributor/gpu_tests/shampoo_fsdp_utils_test.py:55
Methodworld_size
(self)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/distributor/gpu_tests/shampoo_fsdp_utils_test.py:126
Methodworld_size
(self)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/distributor/gpu_tests/shampoo_dist_utils_test.py:28
Methodworld_size
(self)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/distributor/gpu_tests/shampoo_hsdp_distributor_test.py:62
Methodworld_size
(self)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/distributor/gpu_tests/shampoo_hsdp_distributor_test.py:362
Methodwrap_model
( self, model: nn.Module, local_rank: int, backend: str, device_mesh:
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/examples/parallelism.py:46
Functionwrapper
(A: Tensor, *args: object, **kwargs: object)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/preconditioner/matrix_functions.py:110
Functionwrapper
(them: object, *args: Any, **kwargs: Any)
records/track_3_optimization/results/20260513_shampoo_1_4_power/distributed_shampoo/preconditioner/preconditioner_list.py:40
Functionzeropower_via_newtonschulz5
Newton-Schulz iteration to compute the zeroth power / orthogonalization of G. We opt to use a quintic iteration whose coefficients are select
records/track_1_short/2024-12-04_ValueEmbed/train_gpt2.py:31
Functionzeropower_via_newtonschulz5
Newton-Schulz iteration to compute the zeroth power / orthogonalization of G. We opt to use a quintic iteration whose coefficients are select
records/track_1_short/2024-10-14_ModernArch/train_gpt2.py:26
Functionzeropower_via_newtonschulz5
Newton-Schulz iteration to compute the zeroth power / orthogonalization of G. We opt to use a quintic iteration whose coefficients are select
records/track_1_short/2024-10-10_Muon/train_gpt2.py:26
Functionzeropower_via_svd
(G, steps=None)
records/track_1_short/2024-12-04_ValueEmbed/train_gpt2.py:26
Functionzeropower_via_svd
(G, steps=None)
records/track_1_short/2024-10-14_ModernArch/train_gpt2.py:21
Functionzeropower_via_svd
(G, steps=None)
records/track_1_short/2024-10-10_Muon/train_gpt2.py:21
← previous2,301–2,320 of 2,320, ranked by callers