Mamba-QA-ITA-790m / config.json
DeepMount00's picture
Upload 5 files
3d48e4e verified
raw
history blame
201 Bytes
{
"d_model": 1536,
"n_layer": 48,
"vocab_size": 50277,
"ssm_cfg": {},
"rms_norm": true,
"residual_in_fp32": true,
"fused_add_norm": true,
"pad_vocab_size_multiple": 8
}