Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024 This model has 12 layers and the embedding size is 768. Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset. This model is initialized from xlm-roberta-base and continually trained on a mixture of multilingual datasets. It supports 100 languages from xlm-roberta, but low-resource languages may see performance degradation. For all labeled datasets, we only use its training set for fine-tuning. For other training details, please refer to our paper at https://arxiv.org/pdf/2402.05672. Check out unilm/e5 to reproduce evaluation results on the BEIR and MTEB benchmark.…
Open-weight model · Sentence similarity
paraphrase-multilingual-mpnet-base-v2
by Sentence Transformers sentence-transformers/paraphrase-multilingual-mpnet-base-v2
This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
Parameters278M
Context514
Weights10.8 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads9.8M
Runs On
What it takes to serve paraphrase-multilingual-mpnet-base-v2 (278M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.6 GB | 0.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.3 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
Model Card
By Sentence Transformers, published under apache-2.0, revision 4328cf26390c.
This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
Usage (Sentence-Transformers)
Using this model becomes easy when you have sentence-transformers installed:
pip install -U sentence-transformers
Then you can use the model like this:
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/paraphrase-multilingual-mpnet-base-v2')
embeddings = model.encode(sentences)
print(embeddings)
Usage (HuggingFace Transformers)
Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
Configuration
- Architecture
- XLMRobertaModel
- Context length (tokens)
- 514
- Layers
- 12
- Hidden size
- 768
- Feed-forward size
- 3,072
- Attention heads
- 12
- Vocabulary size
- 250,002
- Model type
- xlm-roberta
Identity and Version
- Repository
- sentence-transformers/paraphrase-multilingual-mpnet-base-v2
- Publisher
- Sentence Transformers
- Task
- Sentence similarity
- Modality
- Text
- Library
- sentence-transformers
- Parameters
- 278M parameters
- Languages
- ar, bg, ca, cs, da, de, el, en
- Revision
- 4328cf26390c98c5e3c738b4460a05b95f4911f5
- First published
- 2022-03-02
- Last updated
- 2025-08-19
Files and Weights
27 files, 10.9 GB in total. The weights are 14 files totalling 10.8 GB in bin, h5, onnx, safetensors.
Weights14 files · 10.8 GB
Configuration6 files · 1.6 KB
Tokenizer2 files · 9.1 MB
Documentation1 file · 5.1 KB
Other3 files · 6.2 MB
Repository1 file · 744 B
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.1 GB | b5722100700c |
| onnx/model.onnx | Weights | 1.1 GB | 253e00bb467f |
| onnx/model_O1.onnx | Weights | 1.1 GB | bd9aacd52770 |
| onnx/model_O2.onnx | Weights | 1.1 GB | 04faa200d4c8 |
| onnx/model_O3.onnx | Weights | 1.1 GB | 96a14beec4c3 |
| onnx/model_O4.onnx | Weights | 554.9 MB | 1ce03da9c11f |
| onnx/model_qint8_arm64.onnx | Weights | 278.7 MB | 88784a4b95fd |
| onnx/model_qint8_avx512.onnx | Weights | 278.7 MB | 88784a4b95fd |
| onnx/model_qint8_avx512_vnni.onnx | Weights | 278.7 MB | 88784a4b95fd |
| onnx/model_quint8_avx2.onnx | Weights | 278.8 MB | 82f6b58b509e |
| openvino/openvino_model.bin | Weights | 1.1 GB | 769542d94a9f |
| openvino/openvino_model_qint8_quantized.bin | Weights | 279.4 MB | 02411c6a9007 |
| pytorch_model.bin | Weights | 1.1 GB | 29d10eabb079 |
| tf_model.h5 | Weights | 1.1 GB | 440b08bc2d5e |
| 1_Pooling/config.json | Configuration | 190 B | — |
| config.json | Configuration | 723 B | — |
| config_sentence_transformers.json | Configuration | 122 B | — |
| modules.json | Configuration | 229 B | — |
| sentence_bert_config.json | Configuration | 53 B | — |
| special_tokens_map.json | Configuration | 239 B | — |
| README.md | Documentation | 5.1 KB | — |
| openvino/openvino_model.xml | Other | 408.8 KB | — |
| openvino/openvino_model_qint8_quantized.xml | Other | 719.3 KB | — |
| sentencepiece.bpe.model | Other | 5.1 MB | cfc8146abe2a |
| .gitattributes | Repository | 744 B | — |
| tokenizer.json | Tokenizer | 9.1 MB | — |
| tokenizer_config.json | Tokenizer | 402 B | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 10.8 GB
Download from Sentence Transformers
Released by Sentence Transformers through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:1908.10084
Evaluations
Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| mteb/arguana | Task ArguAnaMetric ArguAnaSetup Obtained using MTEB v1.12.75Comparison conditions not established | 48.908 | Obtained using MTEB v1.12.75 Reported by a third party |
Evaluated revision not stated | 2026-03-05 |
| mteb/arguana | Task ArguAna_default_testMetric ArguAna_default_testSetup Obtained using MTEB v1.12.75Comparison conditions not established | 48.908 | Obtained using MTEB v1.12.75 Reported by a third party |
Evaluated revision not stated | 2026-03-05 |
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 10.8 GB |
| 16-bit | 0.6 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Compare paraphrase-multilingual-mpnet-base-v2
Questions About paraphrase-multilingual-mpnet-base-v2
How much GPU memory does paraphrase-multilingual-mpnet-base-v2 need?
About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (278M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run paraphrase-multilingual-mpnet-base-v2 on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use paraphrase-multilingual-mpnet-base-v2 commercially?
Yes. paraphrase-multilingual-mpnet-base-v2 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
What is paraphrase-multilingual-mpnet-base-v2's context length?
514 tokens, from the maximum position embeddings in its published configuration.
Similar Models
This is a LinkTransformer model. At its core this model this is a sentence transformer model sentence-transformers model- it just wraps around the class. It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more. Notwithstanding that, it can be used for any sentence similarity task within the sentence-transformers framework as well. It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. Take a look at the documentation of sentence-transformers if you want to use this model for more than what we…
This is a LinkTransformer model. At its core this model this is a sentence transformer model sentence-transformers model- it just wraps around the class. It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more. Notwithstanding that, it can be used for any sentence similarity task within the sentence-transformers framework as well. It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. Take a look at the documentation of sentence-transformers if you want to use this model for more than what we…
This is a LinkTransformer model. At its core this model this is a sentence transformer model sentence-transformers model- it just wraps around the class. It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more. Notwithstanding that, it can be used for any sentence similarity task within the sentence-transformers framework as well. It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. Take a look at the documentation of sentence-transformers if you want to use this model for more than what we…
This is a LinkTransformer model. At its core this model this is a sentence transformer model sentence-transformers model- it just wraps around the class. It is designed for quick and easy record linkage (entity-matching) through the LinkTransformer package. The tasks include clustering, deduplication, linking, aggregation and more. Notwithstanding that, it can be used for any sentence similarity task within the sentence-transformers framework as well. It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. Take a look at the documentation of sentence-transformers if you want to use this model for more than what we…
EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages. The small size and on-device focus makes it possible to deploy in environments with limited resources such as mobile phones, laptops, or desktops, democratizing access to state of the art AI models and helping foster innovation for everyone.…