mamba-ko-2.8b / config.json
kuotient's picture
Add architectures
955a663 verified
raw
history blame
224 Bytes
{
"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
}