dtype: float32 in base model vs. dtype: bfloat16 in the instruction fine-tuned model

#32
by tanliboy - opened

In this base model, the dtype is float32; however, in the instruction fine-tuned model, the dtype is (https://huggingface.co/google/gemma-2-9b-it/blob/main/config.json#L29).

Is this inconsistency intentional or a bug?

Sign up or log in to comment