·
AI & ML interests
None yet
Organizations
gerou161/baseline_tying_520m
Updated
gerou161/one_layer_tying_zipf_white_2_freeze_emb_and_out_520m
Updated
gerou161/one_layer_tying_Uni_ZCAWhite_2_freeze_emb_and_out_520m_9e-4
Updated
gerou161/one_layer_tying_zipf_white_bias_2_freeze_emb_and_out_520m
Updated
gerou161/one_layer_tying_Uni_ZCAWhite_2_freeze_emb_and_out_520m_0002
Updated
gerou161/one_layer_tying_Uni_ZCAWhite_bias_unfreeze_2_freeze_emb_and_out_520m
Updated
gerou161/baseline_untying_520m
Updated
gerou161/one_layer_untying_uni_white_2_freeze_emb_and_out_520m
Updated
gerou161/one_layer_untying_1_520m
Updated
gerou161/one_layer_untying_2_freeze_emb_and_out_520m
Updated
gerou161/one_layer_untying_uni_white_1-2_520m
Updated
gerou161/one_layer_untying_1_300m_3e-3
Updated
gerou161/one_layer_untying_2_300m_3e-3
Updated
gerou161/baseline_untying_300m_1e-3
Updated
gerou161/baseline_untying_300m_2e-3
Updated
gerou161/baseline_untying_300m_9e-4
Updated
gerou161/one_layer_untying_2_300m_9e-4
Updated
gerou161/one_layer_untying_1_300m_9e-4
Updated
gerou161/one_layer_untying_1_300m_2e-3
Updated
gerou161/one_layer_untying_1_300m_4e-3
Updated
gerou161/baseline_untying_300m_4e-3
Updated
gerou161/baseline_untying_300m_3e-3
Updated
gerou161/one_layer_untying_1_300m_1e-3
Updated
gerou161/one_layer_untying_2_300m_4e-3
Updated
gerou161/one_layer_untying_2_300m_1e-3
Updated
gerou161/one_layer_untying_2_300m_2e-3
Updated
gerou161/one_layer_tying_2_300m_1e-3
Updated
gerou161/baseline_tying_300m_1.5e-3
Updated
gerou161/one_layer_tying_Singular_Decay_Gamma04_2_300m_2e-3
Updated
gerou161/one_layer_tying_1_300m_4e-3
Updated