{ | |
"architectures": ["MambaForCausalLM"], | |
"d_model": 2560, | |
"n_layer": 64, | |
"vocab_size": 50277, | |
"ssm_cfg": {}, | |
"rms_norm": true, | |
"residual_in_fp32": true, | |
"fused_add_norm": true, | |
"pad_vocab_size_multiple": 8 | |
} |
{ | |
"architectures": ["MambaForCausalLM"], | |
"d_model": 2560, | |
"n_layer": 64, | |
"vocab_size": 50277, | |
"ssm_cfg": {}, | |
"rms_norm": true, | |
"residual_in_fp32": true, | |
"fused_add_norm": true, | |
"pad_vocab_size_multiple": 8 | |
} |