I trying to put a repulsive probe particle in silicon bath but lammps pair_style argument are not correct

units metal
dimension 3
boundary p p p
atom_style atomic

variable a equal 5.431
variable t equal 1800.0

lattice custom $a &
a1 1.0 0.0 0.0 &
a2 0.0 1.0 0.0 &
a3 0.0 0.0 1.0 &
basis 0.5 0.5 0.0 &
basis 0.0 0.5 0.5 &
basis 0.5 0.0 0.5 &
basis 0.25 0.25 0.25 &
basis 0.25 0.75 0.75 &
basis 0.75 0.25 0.75 &
basis 0.75 0.75 0.25

region box block 0 4 0 4 0 4

create_box 2 box
create_atoms 1 box
create_atoms 2 random 1 423412 box

mass 1 28.06
mass 2 28.06

velocity all create $t 12345

pair_style hybrid sw threebody yes sw threebody no
pair_coeff * * sw 1 Si.sw Si NULL
pair_coeff 1 2 sw 2 Si.sw NULL Si
pair_coeff 2 2 sw 2 Si.sw Si 2

neighbor 0.3 bin
neigh_modify every 1 delay 10 check yes

minimize 1.0e-4 1.0e-6 1000 1000
timestep 0.005
thermo 10
thermo_style custom step temp ke pe etotal density vol press

fix 1 all nvt temp $t $t 1.0

dump id all atom 100 SiBath.dump
run_style verlet

run 10000

Can anyone help me figure out this hybrid pair_style command issue?

This is not so much a pair style hybrid problem, but an issue of pair style sw.
Fixing the issue in pair style sw is a bit complex and will take some time.
Instead, you could just use a repulsive-only Lennard-Jones potential. E.g. like this:

pair_style hybrid sw lj/cut 4.295
pair_coeff * * sw Si.sw Si NULL
pair_coeff 1*2 2 lj/cut 0.01745 3.8264
pair_modify pair lj/cut shift yes

thanks for your answer It is working.But could you tell me how to convert lj mass to metal mass .Because here we have to put mass in metal but pair_style in lj.

This statement makes no sense.