·
AI & ML interests
None yet
Organizations
gerou161/one_layer_2_neox_from_neox_570m_lr2e-3_hf
Updated
gerou161/one_layer_2_attn_neox_from_neox_570m_lr2e-3_hf
Updated
gerou161/attn_2_attn_neox_from_neox_570m_lr4e-3_hf
Updated
gerou161/one_layer_2_attn_neox_from_neox_570m_unfreeze_lr9e-4_hf
Updated
gerou161/baseline_neox_570m_lr2e-3_hf
Updated
gerou161/attn_2_neox_from_neox_570m_lr3e-3_hf
Updated
gerou161/one_layer_2_attn_ffn_neox_from_neox_570m_lr8e-4_hf
Updated
gerou161/base_emb_use_2_neox_from_neox_1b_lr7e-4_hf
Updated
gerou161/baseline_all_normal_1b_lr6e-4_hf
Updated
gerou161/baseline_neox_1b_lr5e-4_hf
Updated
gerou161/baseline_all_normal_1b_lr9e-4_hf
Updated
gerou161/one_layer_2_attn_neox_from_neox_1b_lr9e-4_hf
Updated
gerou161/one_layer_2_neox_from_neox_1b_lr9e-4_hf
Updated
gerou161/baseline_neox_1b_lr4e-4_hf
Updated
gerou161/baseline_neox_1b_lr7e-4_hf
Updated
gerou161/one_layer_2_attn_neox_from_neox_1b_lr8e-4_hf
Updated
gerou161/baseline_neox_1b_lr8e-4_hf
Updated
gerou161/attn_twice_1_neox_1b_lr9e-4_hf
Updated
gerou161/base_emb_use_2_neox_from_neox_1b_lr8e-4_hf
Updated
gerou161/baseline_neox_1b_lr9e-4_hf
Updated
gerou161/one_layer_2_neox_from_neox_1b_lr8e-4_hf
Updated
gerou161/attn_twice_1_neox_1b_lr1e-3_hf
Updated
gerou161/one_layer_2_attn_neox_from_neox_1b_lr7e-4_hf
Updated
gerou161/attn_2_attn_neox_from_neox_1b_lr6e-4_hf
Updated
gerou161/base_emb_use_2_neox_from_neox_1b_lr6e-4_hf
Updated
gerou161/one_layer_2_attn_neox_from_neox_1b_lr6e-4_hf
Updated
gerou161/one_layer_2_neox_from_neox_1b_lr7e-4_hf
Updated
gerou161/attn_2_attn_neox_from_neox_1b_lr8e-4_hf
Updated
gerou161/attn_2_attn_neox_from_neox_1b_lr7e-4_hf
Updated
gerou161/one_layer_2_neox_from_neox_1b_lr6e-4_hf
Updated