metadata

license: apache-2.0
language:
  - en
base_model:
  - intfloat/e5-base-unsupervised
pipeline_tag: sentence-similarity

cadet-embed-base-v1

cadet-embed-base-v1 is a BERT-base embedding model fine-tuned from intfloat/e5-base-unsupervised with

cross-encoder listwise distillation (teachers: RankT5-3B and BAAI/bge-reranker-v2.5-gemma2-lightweight)
purely synthetic queries (Llama-3.1 8B generated: questions, claims, titles, keywords, zero-shot & few-shot web queries) over 400k passages total from MSMARCO, DBPedia and Wikipedia corpora.

The result: highly effective BERT-base retrieval.

Quick start

from sentence_transformers import SentenceTransformer
import numpy as np

model = SentenceTransformer("manveertamber/cadet-embed-base-v1")

query = "query: capital of France"

passages = [
    "passage: Paris is the capital and largest city of France.",
    "passage: Berlin is known for its vibrant art scene.",
    "passage: The Eiffel Tower is located in Paris, France."
]

# Encode (embeddings are already L2-normalised by default)
q_emb   = model.encode(query,    normalize_embeddings=True)
p_embs  = model.encode(passages, normalize_embeddings=True)     # shape (n_passages, dim)

# Cosine similarity = dot product of normalised vectors
scores = np.dot(p_embs, q_emb)                                  # shape (n_passages,)

# Rank passages by score
for passage, score in sorted(zip(passages, scores), key=lambda x: x[1], reverse=True):
    print(f"{score:.3f}\t{passage}")

If you use this model, please cite:

@article{tamber2025teaching,
  title={Teaching Dense Retrieval Models to Specialize with Listwise Distillation and LLM Data Augmentation},
  author={Tamber, Manveer Singh and Kazi, Suleman and Sourabh, Vivek and Lin, Jimmy},
  journal={arXiv preprint arXiv:2502.19712},
  year={2025}
}