Something went wrong when running deepmd lammps

[LZYUCL]

**I have updated my deepmd-kit(v2.0.3). Some error occured when I run lammps using deepmd potential, below is the error:

2022-03-05 21:06:49.136509: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: SSE4.1 SSE4.2 AVX AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2022-03-05 21:06:49.143851: I tensorflow/core/common_runtime/process_util.cc:146] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.

Info of model(s):
using 1 model(s): graph.pb
rcut in model: 17
ntypes in model: 4
ERROR: Incorrect args for pair coefficients (src/input.cpp:1713)
Last command: pair_coeff**

And the pair style setting in my input file is below:
pair_style deepmd graph.pb
pair_coeff
neighbor 2.0 bin
neigh_modify every 10 delay 0 check no

There is no error when I used deepmd-kit 1.3 version.
How can I solve it? Thank you!

[LZYUCL]

I have solved this problem, just reinstall deepmd-kit and lammps-dp by
conda create -n deepmd deepmd-kit=2.0.0=*cpu libdeepmd=2.0.0=*cpu lammps-dp=2.0.0 horovod -c https://conda.deepmodeling.org
and set the path to conda envs, and change the submit file.

[njzjz]

In the latest stable version of LAMMPS, you must use pair_coeff * * instead of pair_coeff.
This error is not related to DeePMD-kit.