tokenizer_config.json is different from gemma-2-2b-it
#8
by
dahara1
- opened
Hello! Thank you for the great model.
By the way, regarding the title, I'm particularly concerned that the following doesn't exist. Is this okay?
"additional_special_tokens": [
"<start_of_turn>",
"<end_of_turn>"
],
Don't worry, info about special tokens is stored at the AddedToken level itself, can be ignored!
Thank you for checking, it worked.
Thanks to you, I was able to release a finetuned model for translation tasks. The quality varies greatly depending on the writing style, but I feel that the performance is close to that of the 7B model from a year ago.
https://huggingface.co/webbigdata/gemma-2-2b-jpn-it-translate
dahara1
changed discussion status to
closed