For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our Github.

Usage

📌 Tip: For NV-Embed-V2, using Transformers versions later than 4.47.0 may lead to performance degradation, as model_type=bidir_mistral in config.json is no longer supported.

We recommend using Transformers 4.47.0.

Sentence Transformers Usage

You can evaluate this model loaded by Sentence Transformers with the following code snippet:

import mteb
from sentence_transformers import SparseEncoder

model = SparseEncoder("Y-Research-Group/CSR-NV_Embed_v2-Retrieval-NFcorpus", trust_remote_code=True)
model.prompts = {
    "NFCorpus-query": "Instruct: Given a question, retrieve relevant documents that answer the question\nQuery:"
}

task = mteb.get_tasks(tasks=["NFCorpus"])
evaluation = mteb.MTEB(tasks=task)
evaluation.run(
    model,
    eval_splits=["test"],
    output_folder="./results/NFCorpus",
    show_progress_bar=True,
    encode_kwargs={"convert_to_sparse_tensor": False, "batch_size": 8},
)  # MTEB don't support sparse tensors yet, so we need to convert to dense tensors

Citation

@misc{wen2025matryoshkarevisitingsparsecoding,
      title={Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation}, 
      author={Tiansheng Wen and Yifei Wang and Zequn Zeng and Zhong Peng and Yudi Su and Xinyang Liu and Bo Chen and Hongwei Liu and Stefanie Jegelka and Chenyu You},
      year={2025},
      eprint={2503.01776},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2503.01776}, 
}