How to use albert/albert-xxlarge-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="albert/albert-xxlarge-v1")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("albert/albert-xxlarge-v1") model = AutoModelForMaskedLM.from_pretrained("albert/albert-xxlarge-v1", device_map="auto")
https://huggingface.co/albert/albert-xxlarge-v1/resolve/main/spiece.model
hf download hf://albert/albert-xxlarge-v1/spiece.model
curl -L -o spiece.model https://huggingface.co/albert/albert-xxlarge-v1/resolve/main/spiece.model
