How to use UT/MULTIBRT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="UT/MULTIBRT")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("UT/MULTIBRT") model = AutoModelForSequenceClassification.from_pretrained("UT/MULTIBRT", device_map="auto")
https://huggingface.co/UT/MULTIBRT/resolve/main/tokenizer.json
hf download hf://UT/MULTIBRT/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/UT/MULTIBRT/resolve/main/tokenizer.json
