A ModernBERT model (answerdotai/ModernBERT-base) fine-tuned on NLI and tabular classification datasets using sentence-transformers.
You need transformers>=4.48.0 to use ModernBERT (or install from source using pip install git+https://github.com/huggingface/transformers.git). You might also want to install flash attention: pip install flash-attn.
Usage:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("clembi/ModernBERT-base-embed")
sentences = [
"bi-directional embedding methods are cool",
"I like playing Mario Kart",
"They all got into the Mupalupux and drove south.",
]
embeddings = model.encode(sentences)
- Downloads last month
- -
Model tree for clembi/ModernBERT-base-embed
Base model
answerdotai/ModernBERT-base
from sentence_transformers import SentenceTransformer model = SentenceTransformer("clembi/ModernBERT-base-embed") sentences = [ "In 1831, interesting novels were written in Paris.", "Hugo and Dumas met in the Opera in Paris in 1831.", "Many interesting novels are released in the 21st century.", "A new vegan burger is offered at the counter from now on." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]