Search public pages, research tools, and SAVRN solutions.
Open-weight model · Sentence similarity
by Sentence Transformers sentence-transformers/distiluse-base-multilingual-cased-v2
This is a sentence-transformers model: It maps sentences & paragraphs to a 512 dimensional dense vector space and can be used for tasks like clustering or semantic search.
What it takes to serve distiluse-base-multilingual-cased-v2 (135M 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 | 0.3 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.1 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.
We keep encoders this size for jobs where a GPU is optional. At 135 million parameters and 0.3 gigabytes of memory at 16-bit, this multilingual sentence model fits in the corner of any accelerator, and the cheapest listed setup, one MI300X at $1.85 an hour, only makes sense as a sidecar to something larger on the same card. The format list matters more: safetensors, ONNX, OpenVINO, PyTorch and TensorFlow are all published, so it can run on CPU inference boxes where that hourly rate never applies. Output is a 512-dimensional vector per input.
Apache 2.0 permits commercial use, so it can ship inside a product with only the notices retained. Check two things: the 512-token context means long documents get chunked before embedding, and the repository is 30 files and 5.3 gigabytes across those formats, so pull only what your runtime needs. Its paper is Sentence-BERT, arXiv:1908.10084.
By Sentence Transformers, published under apache-2.0, revision bfe45d0732ca.
This is a sentence-transformers model: It maps sentences & paragraphs to a 512 dimensional dense vector space and can be used for tasks like clustering or semantic search.
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/distiluse-base-multilingual-cased-v2')
embeddings = model.encode(sentences)
print(embeddings)
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
(2): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)
This model was trained by sentence-transformers.
If you find this model helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks:
30 files, 5.3 GB in total. The weights are 16 files totalling 5.3 GB in bin, h5, onnx, safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| 2_Dense/model.safetensors | Weights | 1.6 MB | 0a21b1ce908e |
| 2_Dense/pytorch_model.bin | Weights | 1.6 MB | 64fe81485f48 |
| model.safetensors | Weights | 538.9 MB | e8c2aed21297 |
| onnx/model.onnx | Weights | 539.0 MB | 698b5efe2a2e |
| onnx/model_O1.onnx | Weights | 539.0 MB | 905fe98722b1 |
| onnx/model_O2.onnx | Weights | 539.0 MB | 50dc10f1a1b6 |
| onnx/model_O3.onnx | Weights | 539.0 MB | 3af976017c59 |
| onnx/model_O4.onnx | Weights | 269.5 MB | 2475f5fb6596 |
| onnx/model_qint8_arm64.onnx | Weights | 135.3 MB | c78c64bb0446 |
| onnx/model_qint8_avx512.onnx | Weights | 135.3 MB | c78c64bb0446 |
| onnx/model_qint8_avx512_vnni.onnx | Weights | 135.3 MB | c78c64bb0446 |
| onnx/model_quint8_avx2.onnx | Weights | 135.4 MB | 6a5852e0da9c |
| openvino/openvino_model.bin | Weights | 538.9 MB | 49dd1b2e6642 |
| openvino/openvino_model_qint8_quantized.bin | Weights | 135.7 MB | bf548ee8c71a |
| pytorch_model.bin | Weights | 539.0 MB | 0ea26561995c |
| tf_model.h5 | Weights | 539.1 MB | aae68cf03ba8 |
| 1_Pooling/config.json | Configuration | 190 B | — |
| 2_Dense/config.json | Configuration | 114 B | — |
| config.json | Configuration | 610 B | — |
| config_sentence_transformers.json | Configuration | 122 B | — |
| modules.json | Configuration | 341 B | — |
| sentence_bert_config.json | Configuration | 53 B | — |
| special_tokens_map.json | Configuration | 112 B | — |
| README.md | Documentation | 2.5 KB | — |
| openvino/openvino_model.xml | Other | 217.6 KB | — |
| openvino/openvino_model_qint8_quantized.xml | Other | 372.6 KB | — |
| .gitattributes | Repository | 744 B | — |
| tokenizer.json | Tokenizer | 2.0 MB | — |
| tokenizer_config.json | Tokenizer | 531 B | — |
| vocab.txt | Tokenizer | 995.5 KB | — |
Released by Sentence Transformers through its official repository on Hugging Face. Read the license.
| Precision | Weights in memory |
|---|---|
| As published | 5.3 GB |
| 16-bit | 0.3 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (135M parameters) plus a working margin. A long context needs more.
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.
Yes. distiluse-base-multilingual-cased-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.
512 tokens, from the maximum position embeddings in its published configuration.
This is a sentence-transformers model: It maps sentences & paragraphs to a 512 dimensional dense vector space and can be used for tasks like clustering or semantic search. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: This model was trained by sentence-transformers. If you find this model helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Exciting Update!: nomic-embed-text-v1.5 is now multimodal! nomic-embed-vision-v1.5 is aligned to the embedding space of nomic-embed-text-v1.5, meaning any text embedding is multimodal! Important: the text prompt must include a task instruction prefix, instructing the model which task is being performed. For example, if you are implementing a RAG application, you embed your documents as searchdocument: and embed your user queries as searchquery:. Notice: From transformers v5.5.0 and sentence transformers v5.3.0, trustremotecode=True will no longer be necessary. This will only be possible with the text-only series as of now. This prefix is used for embedding texts as documents, for example as…
nomic-embed-text-v1 is 8192 context length text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks. Exciting Update!: nomic-embed-text-v1 is now multimodal! nomic-embed-vision-v1 is aligned to the embedding space of nomic-embed-text-v1, meaning any text embedding is multimodal! Important: the text prompt must include a task instruction prefix, instructing the model which task is being performed. For example, if you are implementing a RAG application, you embed your documents as searchdocument: and embed your user queries as searchquery:. Notice: From transformers v5.5.0 and sentence transformers v5.3.0…
This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: 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. This model was trained by sentence-transformers. If you find this model helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024 This model has 12 layers and the embedding size is 384. Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset. This model is initialized from microsoft/Multilingual-MiniLM-L12-H384 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…
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 384 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…