How to use models-lab/modeling-bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="models-lab/modeling-bert")
# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("models-lab/modeling-bert") model = AutoModelForMaskedLM.from_pretrained("models-lab/modeling-bert", device_map="auto")
026b6e6
1
2
3
4
5
6
{ "_from_model_config": true, "pad_token_id": 0, "transformers_version": "4.37.2" }
