Alibaba-NLP

/

gte-Qwen1.5-7B-instruct

like 80

加载tokenizer时报错envs/base2/lib/python3.9/site-packages/transformers/models/qwen2/tokenization_qwen2.py", line 179, in init
with open(merges_file, encoding="utf-8") as merges_handle:

TypeError: expected str, bytes or os.PathLike object, not NoneType
tokenization_qwen中包含了字典VOCAB_FILES_NAMES = {
"vocab_file": "vocab.json",
"merges_file": "merges.txt",
"tokenizer_file": "tokenizer.json",
}，但是没有看到merges.txt