Modern BERTScore
Collection
Models for a modern implementation of BERTScore (Zhang et al., 2019) - https://arxiv.org/abs/1904.09675 • 6 items • Updated
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("LazerLambda/roberta-base-ModBERTScore-10")
model = AutoModel.from_pretrained("LazerLambda/roberta-base-ModBERTScore-10", device_map="auto")Quick Links
RoBERTa-large Model for modern-bert-score
Model based on FacebookAI/roberta-base, using only the first 10 transformer layers.
- Downloads last month
- 10
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="LazerLambda/roberta-base-ModBERTScore-10")