| { | |
| "vocab": 50257, | |
| "sequence": 256, | |
| "n_layers": 4, | |
| "n_embed": 12288, | |
| "aft_kind": "conv", | |
| "aft_heads": 4, | |
| "aft_ksize": 4, | |
| "dyt_alpha": 0.5, | |
| "linear_fan_in": 4, | |
| "attn_fan_in": null, | |
| "mlp_fan_in": null, | |
| "tanh_linear": true, | |
| "tanh_mlp": true, | |
| "remat": true | |
| } | |