{ | |
"dim": 4096, | |
"n_layers": 64, | |
"vocab_size": 32768, | |
"n_groups": 8, | |
"rms_norm": true, | |
"residual_in_fp32": true, | |
"fused_add_norm": true, | |
"pad_vocab_size_multiple": 1, | |
"tie_embeddings": false, | |
"model_type": "mamba" | |
} | |
{ | |
"dim": 4096, | |
"n_layers": 64, | |
"vocab_size": 32768, | |
"n_groups": 8, | |
"rms_norm": true, | |
"residual_in_fp32": true, | |
"fused_add_norm": true, | |
"pad_vocab_size_multiple": 1, | |
"tie_embeddings": false, | |
"model_type": "mamba" | |
} | |