NeoQuasar/Kronos-base
2761m
1{2 "attn_dropout_p": 0.0,3 "d_model": 832,4 "ff_dim": 2048,5 "ffn_dropout_p": 0.2,6 "learn_te": true,7 "n_heads": 16,8 "n_layers": 12,9 "resid_dropout_p": 0.2,10 "s1_bits": 10,11 "s2_bits": 10,12 "token_dropout_p": 0.013}