I got the error on centos 7: failed to tokenize string!

I got the error like this on centos 7:
failed to tokenize string!

[root@VM-0-15-centos build]# ./llama -m chinese-alpaca-7b-q4.bin -t 2
main: seed = 1700961097
model is new , version = 1
load: n_vocab = 49954
load: n_ctx = 2048
load: n_embd = 4096
load: n_mult = 256
load: n_head = 32
load: n_layer = 32
load: n_rot = 128
load: model ftype = 2
total weight length = 4304332800
main: interactive mode on.
sampling parameters: temp = 0.100000, top_k = 40, top_p = 0.950000, repeat_last_n = 64, repeat_penalty = 1.300000

== Running in chat mode. ==
- Press Ctrl+C to interject at any time.
- If you want to submit another line, end your input in '\'.
failed to tokenize string!
Killed

_Originally posted by @Mignet in https://github.com/MegEngine/InferLLM/issues/28#issuecomment-1826459644_

Start by reproducing the reported command on CentOS 7 with chinese-alpaca-7b-q4.bin and two threads. Investigate the tokenizer failure shown after entering chat mode; done means identifying the cause and confirming that the same invocation no longer exits with the reported error and Killed message.

Written by the indexing model from the issue text.