llama Llama baseline checkpoints (0.6B, 1.3B) CharlesDDDD/llama_0.6B_100bt_formal Updated Feb 4 • 2 CharlesDDDD/llama_1.3B_100bt_formal Updated Feb 4 • 15
looped_transformer Looped transformer checkpoint collection CharlesDDDD/looped_window_600M_full_512_256_128_weighted_loss Updated Feb 4 CharlesDDDD/looped_600M_bookend_2_looped4_window_128 Updated Feb 4 • 1 CharlesDDDD/looped_600M_4to1_looped1_window_128 Updated Feb 4 • 4 CharlesDDDD/looped_transformer_loop_count_4 Updated Feb 5 • 3
llama Llama baseline checkpoints (0.6B, 1.3B) CharlesDDDD/llama_0.6B_100bt_formal Updated Feb 4 • 2 CharlesDDDD/llama_1.3B_100bt_formal Updated Feb 4 • 15
looped_transformer Looped transformer checkpoint collection CharlesDDDD/looped_window_600M_full_512_256_128_weighted_loss Updated Feb 4 CharlesDDDD/looped_600M_bookend_2_looped4_window_128 Updated Feb 4 • 1 CharlesDDDD/looped_600M_4to1_looped1_window_128 Updated Feb 4 • 4 CharlesDDDD/looped_transformer_loop_count_4 Updated Feb 5 • 3