metadata
license: mit
datasets:
- mteb/mtop_intent
language:
- en
pipeline_tag: text-classification
library_name: sentence-transformers
tags:
- mteb
- text
- transformers
- text-embeddings-inference
- sparse-encoder
- sparse
- csr
model-index:
- name: CSR
results:
- dataset:
name: MTEB MTOPIntentClassification (en)
type: mteb/mtop_intent
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
config: en
split: test
languages:
- eng-Latn
metrics:
- type: accuracy
value: 0.906407
- type: f1
value: 0.694457
- type: f1_weighted
value: 0.917326
- type: main_score
value: 0.906407
task:
type: Classification
- dataset:
name: MTEB MTOPIntentClassification (de)
type: mteb/mtop_intent
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
config: de
split: test
languages:
- deu-Latn
metrics:
- type: accuracy
value: 0.851
- type: f1
value: 0.601279
- type: f1_weighted
value: 0.863969
- type: main_score
value: 0.851
task:
type: Classification
- dataset:
name: MTEB MTOPIntentClassification (es)
type: mteb/mtop_intent
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
config: es
split: test
languages:
- spa-Latn
metrics:
- type: accuracy
value: 0.906738
- type: f1
value: 0.642295
- type: f1_weighted
value: 0.910882
- type: main_score
value: 0.906738
task:
type: Classification
- dataset:
name: MTEB MTOPIntentClassification (fr)
type: mteb/mtop_intent
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
config: fr
split: test
languages:
- fra-Latn
metrics:
- type: accuracy
value: 0.849045
- type: f1
value: 0.59923
- type: f1_weighted
value: 0.863301
- type: main_score
value: 0.849045
task:
type: Classification
- dataset:
name: MTEB MTOPIntentClassification (hi)
type: mteb/mtop_intent
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
config: hi
split: test
languages:
- hin-Deva
metrics:
- type: accuracy
value: 0.751094
- type: f1
value: 0.44095
- type: f1_weighted
value: 0.762567
- type: main_score
value: 0.751094
task:
type: Classification
- dataset:
name: MTEB MTOPIntentClassification (th)
type: mteb/mtop_intent
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
config: th
split: test
languages:
- tha-Thai
metrics:
- type: accuracy
value: 0.75566
- type: f1
value: 0.498529
- type: f1_weighted
value: 0.76994
- type: main_score
value: 0.75566
task:
type: Classification
base_model:
- nvidia/NV-Embed-v2
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-Classification-MTOPIntent",
trust_remote_code=True
)
model.prompts = {
"MTOPIntentClassification": "Instruct: Classify the intent of the given utterance in task-oriented conversation\nQuery:"
}
task = mteb.get_tasks(tasks=["MTOPIntentClassification"])
evaluation = mteb.MTEB(tasks=task)
evaluation.run(model,
eval_splits=["test"],
output_folder="./results/MTOPIntentClassification",
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
@inproceedings{wenbeyond,
title={Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation},
author={Wen, Tiansheng and Wang, Yifei and Zeng, Zequn and Peng, Zhong and Su, Yudi and Liu, Xinyang and Chen, Bo and Liu, Hongwei and Jegelka, Stefanie and You, Chenyu},
booktitle={Forty-second International Conference on Machine Learning}
}