i-be-snek/dense_eng_100m_mult_het_retok-hom
Updated
shorouq
i-be-snek
AI & ML interests
There be only one rule. No step on snek.
Recent Activity
new activity 5 days ago
facebook/flores:Convert dataset to Parquet published a model 14 days ago
i-be-snek/train-tokBY-arb_arab-zho_hans-fin_latn-fra_latn-tur_latn-1000mb_dom_tok_gpt2moe updated a model about 1 month ago
i-be-snek/train-tokBY-arb_arab-zho_hans-fin_latn-fra_latn-tur_latn-1000mb_dom_tok_gpt2moeOrganizations
i-be-snek/dense_eng_100m_mult_hom_retok-hom
Text Generation • 0.2B • Updated
i-be-snek/dense_eng_100m_mult_het_retok-het
Text Generation • 0.2B • Updated
i-be-snek/moe_het_100m_dist
Text Generation • 0.3B • Updated
i-be-snek/dense_swe_100m_mult_retok
Text Generation • 0.2B • Updated
i-be-snek/moe_hom_100m
Text Generation • 0.3B • Updated
i-be-snek/dense_hom_100m
Text Generation • 0.2B • Updated
i-be-snek/dense_eng_100m_mult_het
Text Generation • 0.2B • Updated
i-be-snek/dense_ell_100m_mult
Text Generation • 0.2B • Updated
i-be-snek/dense_isl_100m_mult
Text Generation • 0.2B • Updated
i-be-snek/dense_eng_100m_mult_hom
Text Generation • 0.2B • Updated
i-be-snek/dense_dan_100m_mult
Text Generation • 0.2B • Updated
i-be-snek/dense_swe_100m_mult
Text Generation • 0.2B • Updated
i-be-snek/dense_nor_100m_mult
Text Generation • 0.2B • Updated
i-be-snek/dense_arb_100m_mult
Text Generation • 0.2B • Updated
i-be-snek/dense_est_100m_mult
Text Generation • 0.2B • Updated
i-be-snek/moe_g_medium_8exp
Text Generation • 0.4B • Updated
i-be-snek/moe_het_100m
Text Generation • 0.3B • Updated
i-be-snek/moe_tur_multi_batch_8
Text Generation • 0.5B • Updated
i-be-snek/moe_g_topk_1
Text Generation • 0.5B • Updated
i-be-snek/moe_g_smaller
Text Generation • 0.2B • Updated
i-be-snek/moe_g_fewer
Text Generation • 0.4B • Updated
i-be-snek/moe_tur_multi_batch_16
Text Generation • 0.5B • Updated
i-be-snek/moe_tur_mono
Text Generation • 0.5B • Updated
i-be-snek/moe_tur_multi_lr_x4
Text Generation • 0.5B • Updated
i-be-snek/moe_tur_multi_lr_x2
Text Generation • 0.5B • Updated
i-be-snek/dense_tur_mono
Text Generation • 0.1B • Updated
i-be-snek/moe_tur_multi
Text Generation • 0.5B • Updated
i-be-snek/dense_tur_mono_old
Text Generation • 0.2B • Updated
i-be-snek/dense_tur_100m_mult
Text Generation • 0.2B • Updated • 6