·
AI & ML interests
None yet
Organizations
gerou161/one_layer_untying_2_300m_2e-3_init0.00250
gerou161/one_layer_untying_2_300m_2e-3_init0.00250_scaled_2
gerou161/one_layer_untying_2_300m_2e-3_init0.00333_scaled_16
gerou161/one_layer_untying_2_300m_2e-3_init0.00500
gerou161/one_layer_untying_2_300m_2e-3_init0.00250_scaled_4
gerou161/one_layer_untying_2_300m_2e-3_init0.00333
gerou161/one_layer_untying_2_300m_2e-3_init0.00500_scaled_4
gerou161/one_layer_untying_2_300m_2e-3_init0.00500_scaled_16
gerou161/one_layer_untying_2_300m_2e-3_init0.00500_scaled_2
gerou161/one_layer_untying_2_300m_2e-3_init0.00333_scaled_8
gerou161/one_layer_untying_2_300m_2e-3_init0.01000
gerou161/one_layer_untying_2_300m_2e-3_init0.00250_scaled_16
gerou161/one_layer_untying_2_300m_8e-4_init0.01000
gerou161/one_layer_untying_2_300m_2e-3_init0.00500_scaled_8
gerou161/one_layer_untying_2_300m_2e-3_init0.00333_scaled_4
gerou161/one_layer_untying_2_300m_2e-3_init0.00250_scaled_8
gerou161/one_layer_untying_2_300m_8e-4_init0.00333
gerou161/one_layer_untying_2_300m_2e-3_init0.00333_scaled_2
gerou161/one_layer_tying_uni_white_random_bias_2_freeze_emb_and_out_520m
Updated
gerou161/one_layer_tying_uni_white_1-2_520m
Updated
gerou161/one_layer_tying_2_freeze_emb_and_out_520m
Updated
gerou161/one_layer_tying_uni_white_bias_unfreeze_2_freeze_emb_and_out_520m
Updated
gerou161/one_layer_tying_2_unfreeze_emb_and_out_520m
Updated
gerou161/one_layer_tying_uni_white_2_freeze_emb_and_out_520m
Updated
gerou161/one_layer_tying_uni_white_bias_2_freeze_emb_and_out_520m
Updated
gerou161/base_emb_use_2_freeze_emb_and_out_520m
Updated
gerou161/one_layer_tying_Uni_ZCAWhite_2_freeze_emb_and_out_520m
Updated
gerou161/one_layer_tying_1_520m
Updated
gerou161/one_layer_tying_Uni_ZCAWhite_2_freeze_emb_and_out_520m_0003_9e-4
Updated
gerou161/one_layer_tying_Uni_ZCAWhite_bias_2_freeze_emb_and_out_520m
Updated