py : also print the normalizers

This commit is contained in:
Georgi Gerganov 2024-05-08 12:47:07 +03:00
parent acdce3cdef
commit 7e0b6a7b3b
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735

View File

@ -151,6 +151,8 @@ for model in models:
# print the "pre_tokenizer" content from the tokenizer.json
with open(f"models/tokenizers/{name}/tokenizer.json", "r", encoding="utf-8") as f:
cfg = json.load(f)
normalizer = cfg["normalizer"]
logger.info("normalizer: " + json.dumps(normalizer, indent=4))
pre_tokenizer = cfg["pre_tokenizer"]
logger.info("pre_tokenizer: " + json.dumps(pre_tokenizer, indent=4))