KoichiYasuoka
/

Xunzi-Qwen1.5-7B-upos

Token Classification

Literary Chinese

classical chinese

literary chinese

ancient chinese

dependency-parsing

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Xunzi-Qwen1.5-7B-upos / mergeout.sh

KoichiYasuoka's picture

emulate tokenize_chinese_chars=True

a6bc6a0 4 months ago

92 Bytes

	#! /usr/bin/egrep -vf
	^ã[^ĢģĤĥĦħĨĩĪīĬĭĮįİı ][^ ]
	^[ãäåæçèé][^ ][^ ]