Fix warning message on LLaMA FastTokenizer (#1037)

This commit is contained in:
Woosuk Kwon 2023-09-14 17:33:32 -07:00 committed by GitHub
parent b5f93d0631
commit 64ca424e75
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -28,8 +28,8 @@ def get_tokenizer(
if ("llama" in tokenizer_name.lower() and kwargs.get("use_fast", True)
and tokenizer_name != _FAST_LLAMA_TOKENIZER):
logger.info(
"For some LLaMA-based models, initializing the fast tokenizer may "
"take a long time. To eliminate the initialization time, consider "
"For some LLaMA V1 models, initializing the fast tokenizer may "
"take a long time. To reduce the initialization time, consider "
f"using '{_FAST_LLAMA_TOKENIZER}' instead of the original "
"tokenizer.")
try:
@ -41,9 +41,9 @@ def get_tokenizer(
except TypeError as e:
# The LLaMA tokenizer causes a protobuf error in some environments.
err_msg = (
"Failed to load the tokenizer. If you are using a LLaMA-based "
f"model, use '{_FAST_LLAMA_TOKENIZER}' instead of the original "
"tokenizer.")
"Failed to load the tokenizer. If you are using a LLaMA V1 model "
f"consider using '{_FAST_LLAMA_TOKENIZER}' instead of the "
"original tokenizer.")
raise RuntimeError(err_msg) from e
except ValueError as e:
# If the error pertains to the tokenizer class not existing or not