MODEL_ARGS=( --swiglu --num-layers 36 --hidden-size 4096 --ffn-hidden-size 12288 --num-attention-heads 32 --group-query-attention --num-query-groups 8 --use-rotary-position-embeddings --disable-bias-linear --normalization "RMSNorm" --norm-epsilon 1e-6 --rotary-base "${MODEL_ARGS_ROTARY_BASE:-1000000}" --vocab-size 151936 --kv-channels 128 --qk-layernorm --untie-embeddings-and-output-weights )