| { | |
| "attn_dropout_p": 0.0, | |
| "beta": 0.05, | |
| "d_in": 6, | |
| "d_model": 256, | |
| "ff_dim": 512, | |
| "ffn_dropout_p": 0.0, | |
| "gamma": 1.1, | |
| "gamma0": 1.0, | |
| "group_size": 4, | |
| "n_dec_layers": 4, | |
| "n_enc_layers": 4, | |
| "n_heads": 4, | |
| "resid_dropout_p": 0.0, | |
| "s1_bits": 10, | |
| "s2_bits": 10, | |
| "zeta": 0.05 | |
| } |