mamba_nli_ensemble / config.json
w06618pm
upload initial unoptimized model
1e807a4
raw
history blame contribute delete
224 Bytes
{
"d_model": 768,
"d_intermediate": 0,
"n_layer": 24,
"vocab_size": 50277,
"ssm_cfg": {},
"rms_norm": true,
"residual_in_fp32": true,
"fused_add_norm": true,
"pad_vocab_size_multiple": 8
}