Research Archive
Collection
Historical artifacts from SBERT-WK, RSE, InstructDS, and earlier research. No longer maintained; retained for reproducibility. • 32 items • Updated
# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("binwang/roberta-base")
model = AutoModelForMaskedLM.from_pretrained("binwang/roberta-base", device_map="auto")Quick Links
Historical research checkpoint — SBERT-WK (2020)
No longer actively maintained. Retained for reproducibility of the original work.
This repository hosts the original 12-layer RoBERTa checkpoint used in the SBERT-WK experiments. It is a supporting checkpoint for the sentence embedding method.
For the paper, original software environment, and reproduction instructions, see SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models.
- Downloads last month
- 29
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="binwang/roberta-base")