How to use google-bert/bert-base-chinese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="google-bert/bert-base-chinese")
# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-chinese") model = AutoModelForMaskedLM.from_pretrained("google-bert/bert-base-chinese")
How much GPU memory did you use to load this model? Why does my GPU usage jump to nearly 20GB when I download and load the weights myself? Is this normal?looks i can barely do fine-tuning then
Β· Sign up or log in to comment
