# distiluse-base-multilingual-cased-v2 by Sentence Transformers Source: https://savrn.com/models/distiluse-base-multilingual-cased-v2 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On 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](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.1 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 23, 2026. [distiluse-base-multilingual-cased-v2 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/distiluse-base-multilingual-cased-v2/gpus) ## SAVRN's Notes on distiluse-base-multilingual-cased-v2 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. SAVRN Research, 2026-09-18 ## Model Card By Sentence Transformers, published under apache-2.0, revision bfe45d0732ca. This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 512 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](https://www.SBERT.net) 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) ``` ### Full Model Architecture ``` 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'}) ) ``` ### Citing & Authors This model was trained by [sentence-transformers](https://www.sbert.net/). If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://savrn.com/papers/sentence-bert-sentence-embeddings-using-siamese-bert-networks): [Read the full model card (183 words)](https://savrn.com/models/distiluse-base-multilingual-cased-v2/card) ## Configuration Architecture DistilBertModel Context length (tokens) 512 Vocabulary size 119,547 Model type distilbert ## Identity and Version Repository sentence-transformers/distiluse-base-multilingual-cased-v2 Publisher Sentence Transformers Task Sentence similarity Modality Text Library sentence-transformers Parameters 135M parameters Languages ar, bg, ca, cs, da, de, el, en Revision bfe45d0732ca50787611c0fe107ba278c7f3f889 First published 2022-03-02 Last updated 2025-03-06 ## Files and Weights 30 files, 5.3 GB in total. The weights are 16 files totalling 5.3 GB in bin, h5, onnx, safetensors. Weights16 files · 5.3 GB Configuration7 files · 1.5 KB Tokenizer3 files · 3.0 MB Documentation1 file · 2.5 KB Other2 files · 590.2 KB Repository1 file · 744 B Every file | 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 | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 5.3 GB [Download from Sentence Transformers](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2) Released by Sentence Transformers through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by [arXiv:1908.10084](https://savrn.com/papers/sentence-bert-sentence-embeddings-using-siamese-bert-networks) ## Memory Requirements | 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. ## Compare distiluse-base-multilingual-cased-v2 - [distiluse-base-multilingual-cased-v2 vs nomic-embed-text-v1](https://savrn.com/models/compare/distiluse-base-multilingual-cased-v2-vs-nomic-embed-text-v1) - [distiluse-base-multilingual-cased-v2 vs nomic-embed-text-v1.5](https://savrn.com/models/compare/distiluse-base-multilingual-cased-v2-vs-nomic-embed-text-v1-5) ## Questions About distiluse-base-multilingual-cased-v2 ### How much GPU memory does distiluse-base-multilingual-cased-v2 need? 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. ### What is the cheapest GPU to run distiluse-base-multilingual-cased-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 distiluse-base-multilingual-cased-v2 commercially? 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. ### What is distiluse-base-multilingual-cased-v2's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Sentence similarity ### [distiluse-base-multilingual-cased-v1](https://savrn.com/models/distiluse-base-multilingual-cased-v1) [Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers) 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 Open weights apache-2.0 135M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/distiluse-base-multilingual-cased-v1) Model · Sentence similarity ### [nomic-embed-text-v1.5](https://savrn.com/models/nomic-embed-text-v1-5) [Nomic AI](https://savrn.com/model-publishers/nomic-ai) 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… Open weights apache-2.0 137M parameters 2,048 tokens sentence-transformers [View model](https://savrn.com/models/nomic-embed-text-v1-5) Model · Sentence similarity ### [nomic-embed-text-v1](https://savrn.com/models/nomic-embed-text-v1) [Nomic AI](https://savrn.com/model-publishers/nomic-ai) 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… Open weights apache-2.0 137M parameters 8,192 tokens sentence-transformers [View model](https://savrn.com/models/nomic-embed-text-v1) Model · Sentence similarity ### [issue-loc-embed-small](https://savrn.com/models/issue-loc-embed-small) [Chao Ma](https://savrn.com/model-publishers/ickma2311) A 137M bi-encoder that ranks the functions of a repository by how likely they need to change to resolve a GitHub issue. It is nomic-ai/CodeRankEmbed (MIT) fine-tuned with an independent re-implementation of the SweRank data recipe (arXiv 2505.07849) on permissively licensed repositories only. No SweRank code or weights were used for training, filtering or mining. Licence: Apache-2.0. v0.2 (this revision, tag v0.2) was trained on Python and on Go, TypeScript, JavaScript, Rust, Java, PHP, C and C++ issues. v0.1 (Python only, the first release) stays available under the tag v0.1. The model's remote code (from CodeRankEmbed) reads the weights of the default branch even when revision= is given… Open weights apache-2.0 137M parameters sentence-transformers [View model](https://savrn.com/models/issue-loc-embed-small) Model · Sentence similarity ### [KielEmbed-Code](https://savrn.com/models/kielembed-code) [Tech](https://savrn.com/model-publishers/kiel2) This is a sentence-transformers model finetuned from microsoft/codebert-base. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more. First install the Sentence Transformers library: Then you can load this model and run inference. Approximate statistics based on the first 100 samples: - numtrainepochs: 1 - learningrate: 2e-05 - warmupsteps: 0.1 - gradientaccumulationsteps: 4 - fp16: True - perdevicetrainbatchsize: 8 - numtrainepochs: 1 - maxsteps: -1 - learningrate: 2e-05 - lrschedulertype: linear - lrschedulerkwargs: None - warmupsteps: 0.1 - optim… Open weights 125M parameters 514 tokens sentence-transformers [View model](https://savrn.com/models/kielembed-code) Model · Sentence similarity ### [lateon-msmarco-hardneg-n10573-e1-ckpt82-qd1024](https://savrn.com/models/lateon-msmarco-hardneg-n10573-e1-ckpt82-qd1024) [Dangerousmanleebyeonggeon](https://savrn.com/model-publishers/dangerousmanleebyeonggeon) This is a PyLate model finetuned from lightonai/LateOn. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator. Use this model with PyLate to index and retrieve documents. The index uses FastPLAID for efficient similarity search. Load the ColBERT model and initialize the PLAID index, then encode and index your documents: Note that you do not have to recreate the index and encode the documents every time. Once you have created an index and added the documents, you can re-use the index later by loading it: Once the documents are indexed, you can retrieve the top-k most relevant documents for a… Open weights 149M parameters 8,192 tokens PyLate [View model](https://savrn.com/models/lateon-msmarco-hardneg-n10573-e1-ckpt82-qd1024) ## Sentence Transformers [All models and datasets](https://savrn.com/model-publishers/sentence-transformers) ## Versions - [bfe45d0732ca](https://savrn.com/models/distiluse-base-multilingual-cased-v2/versions/bfe45d0732ca) · current 2026-09-28 ## Explore More - [All sentence similarity models](https://savrn.com/models/tasks/sentence-similarity) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-19. - [Sentence Transformers website](https://sbert.net/) - [Hugging Face record](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2) - [How the hub is built](https://savrn.com/model-hub/methodology)