vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

convert : exercise contractions

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-04-28 22:18:20 +03:00
parent 0f9058ceec
commit 78081502e9
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
3 changed files with 7 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

2
convert-hf-to-gguf-update.py
View file

@ -36,7 +36,7 @@ class TOKENIZER_TYPE(IntEnum):
# TODO: this string has to exercise as much pre-tokenizer functionality as possible
# will be updated with time - contributions welcome
chktxt = '\n \n\n \n\n\n \t \t\t \t\n \n \n \n \n🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ 🦙🦙 3 33 333 3333 33333 333333 3333333 33333333 3.3 3..3 3...3 កាន់តែពិសេសអាច😁 ?我想在apple工作1314151天～ ------======= нещо на Български what\'s \'\'\'\'\'\'```````\"\"\"\"......!!!!!!??????'
chktxt = '\n \n\n \n\n\n \t \t\t \t\n \n \n \n \n🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ 🦙🦙 3 33 333 3333 33333 333333 3333333 33333333 3.3 3..3 3...3 កាន់តែពិសេសអាច😁 ?我想在apple工作1314151天～ ------======= нещо на Български \'\'\'\'\'\'```````\"\"\"\"......!!!!!!?????? I\'ve been \'told he\'s there, \'RE you sure? \'M not sure I\'ll make it, \'D you like some tea? We\'Ve a\'lL'
if len(sys.argv) == 2:
token = sys.argv[1]