"--disable-bias-linear"
"--num-layers"
"61"
"--hidden-size"
"7168"
"--ffn-hidden-size"
"18432"
"--num-attention-heads"
"64"
"--kv-channels"
"64"
"--normalization"
"RMSNorm"
"--position-embedding-type"
"rope"
"--rope-type"
"yarn"
"--norm-epsilon"
"1e-6"
"--swiglu"
"--untie-embeddings-and-output-weights"
"--vocab-size"
"163840"
"--multi-latent-attention"
"--q-lora-rank"
"1536"
"--kv-lora-rank"
"512"
"--qk-head-dim"
"128"
"--qk-pos-emb-head-dim"
"64"
"--v-head-dim"
"128"
"--qk-layernorm"
"--rotary-scaling-factor"
"32.0"
"--rotary-base"
"50000"
"--original-max-position-embeddings"
"4096"
"--beta-fast"
"1"
"--beta-slow"
"1"
"--mscale"
"1.0"
"--mscale-all-dim"
"1.0"
"--attention-softmax-in-fp32"
"--no-rope-fusion"
"--num-experts"
"384"
"--moe-layer-freq"
"[0,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]"
"--moe-ffn-hidden-size"
"2048"
"--moe-router-topk"
"8"
"--moe-shared-expert-intermediate-size"
"2048"
"--moe-router-pre-softmax"
"--moe-router-score-function"
"sigmoid"
"--moe-router-enable-expert-bias"
"--moe-router-load-balancing-type"
"seq_aux_loss"
"--moe-token-dispatcher-type"
"alltoall"
"--moe-aux-loss-coeff"
"0"
"--moe-router-bias-update-rate"
"0"
"--moe-router-group-topk"
"1"
"--moe-router-num-groups"
"1"
"--moe-grouped-gemm"
"--moe-router-topk-scaling-factor"
"2.827"
"--moe-router-dtype"
"fp32"
"--moe-permute-fusion"
