How to use rzhai/efficient_mlm_m0.05 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="rzhai/efficient_mlm_m0.05")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("rzhai/efficient_mlm_m0.05") model = AutoModelForMaskedLM.from_pretrained("rzhai/efficient_mlm_m0.05", device_map="auto")
Trained using https://github.com/princeton-nlp/DinkyTrain. Mask rate = 0.05.
