Closed polm-stability closed 10 months ago
import sentencepiece as spm
model = spm.SentencePieceProcessor("chinese_sp.model")
# same result as ...
model = spm.SentencePieceProcessor()
model.Load("chinese_sp.model")
I encountered no error with the code above.
My sentencepiece version is sentencepiece==0.1.99
Thanks for the quick reply. I tried re-downloading the model and it was fine, I must have gotten a bad version somehow. Sorry for the noise.
Check before submitting issues
Type of Issue
Other issues
Base Model
None
Operating System
Linux
Describe your issue in detail
I am looking at how the tokenizer for the model was created. The merge script looks fine, but the
chinese_sp.model
file doesn't seem to open in SentencePiece, and I get an error. Is there an issue with the file in the repo, or am I doing something wrong?I thought this might be a protobuf error, but using the
os.environ
setting from the merge script doesn't change the error.Dependencies (must be provided for code-related issues)
Execution logs or screenshots