How to use Twitter/twhin-bert-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="Twitter/twhin-bert-base")
# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("Twitter/twhin-bert-base") model = AutoModelForMaskedLM.from_pretrained("Twitter/twhin-bert-base")
Could you add the ONNX (quantized) version to this repo to be compatible with transformers.js?
· Sign up or log in to comment
