Lanni-ni/dynamic_alibi_4_6_384_inverse_babylm_10m_seed43_epoch8 Text Generation • 45.7M • Updated Sep 6 • 63
Lanni-ni/dynamic_alibi_4_6_384_inverse_babylm_10m_seed43_epoch7 Text Generation • 45.7M • Updated Sep 6 • 61
Lanni-ni/dynamic_alibi_4_6_384_inverse_babylm_10m_seed43_epoch6 Text Generation • 45.7M • Updated Sep 6 • 64
Lanni-ni/dynamic_alibi_4_6_384_inverse_babylm_10m_seed43_epoch5 Text Generation • 45.7M • Updated Sep 6 • 61
Lanni-ni/dynamic_alibi_4_6_384_inverse_babylm_10m_seed43_epoch4 Text Generation • 45.7M • Updated Sep 6 • 62
Lanni-ni/dynamic_alibi_4_6_384_inverse_babylm_10m_seed43_epoch3 Text Generation • 45.7M • Updated Sep 6 • 61
Lanni-ni/dynamic_alibi_4_6_384_inverse_babylm_10m_seed43_epoch2 Text Generation • 45.7M • Updated Sep 6 • 73
Lanni-ni/dynamic_alibi_4_6_384_inverse_babylm_10m_seed43_epoch1 Text Generation • 45.7M • Updated Sep 6 • 61
Lanni-ni/dynamic_alibi_4_6_384_babylm_10m_seed43_epoch10 Text Generation • 45.7M • Updated Sep 6 • 61
Lanni-ni/dynamic_alibi_2_4_256_inverse_babylm_10m_seed43_epoch10 Text Generation • 27.4M • Updated Sep 6 • 64
Lanni-ni/dynamic_alibi_2_4_256_inverse_babylm_10m_seed43_epoch9 Text Generation • 27.4M • Updated Sep 6 • 69
Lanni-ni/dynamic_alibi_2_4_256_inverse_babylm_10m_seed43_epoch8 Text Generation • 27.4M • Updated Sep 6 • 63
Lanni-ni/dynamic_alibi_2_4_256_inverse_babylm_10m_seed43_epoch7 Text Generation • 27.4M • Updated Sep 6 • 64
Lanni-ni/dynamic_alibi_2_4_256_inverse_babylm_10m_seed43_epoch6 Text Generation • 27.4M • Updated Sep 6 • 78
Lanni-ni/dynamic_alibi_2_4_256_inverse_babylm_10m_seed43_epoch5 Text Generation • 27.4M • Updated Sep 6 • 64
Lanni-ni/dynamic_alibi_2_4_256_inverse_babylm_10m_seed43_epoch4 Text Generation • 27.4M • Updated Sep 6 • 64
Lanni-ni/dynamic_alibi_2_4_256_inverse_babylm_10m_seed43_epoch3 Text Generation • 27.4M • Updated Sep 6 • 63
Lanni-ni/dynamic_alibi_2_4_256_inverse_babylm_10m_seed43_epoch2 Text Generation • 27.4M • Updated Sep 6 • 66
Lanni-ni/dynamic_alibi_2_4_256_inverse_babylm_10m_seed43_epoch1 Text Generation • 27.4M • Updated Sep 6 • 71
Lanni-ni/dynamic_forgetting_4_6_384_babylm_100m_seed44_epoch10 Text Generation • 45.7M • Updated Sep 6 • 85
Lanni-ni/dynamic_forgetting_4_6_384_babylm_100m_seed44_epoch9 Text Generation • 45.7M • Updated Sep 6 • 127