| { | |
| "d_model": 4096, | |
| "ssm_cfg": { | |
| "expand": 1, | |
| "ngroups": 32, | |
| "d_state": 128, | |
| "repeat_kv_before_conv": false | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "vocab_size": null, | |
| "d_inner": 4096, | |
| "d_xb": 1024, | |
| "intermediate_size": 14336, | |
| "hidden_act": "silu", | |
| "n_layer": 32, | |
| "attn_layers": [ | |
| 1, | |
| 3, | |
| 5, | |
| 7, | |
| 9, | |
| 11, | |
| 13, | |
| 15, | |
| 17, | |
| 19, | |
| 21, | |
| 23, | |
| 25, | |
| 27, | |
| 29, | |
| 31 | |
| ] | |
| } |