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 1024 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…
Open-weight model · Sentence similarity
all-roberta-large-v1
by Sentence Transformers sentence-transformers/all-roberta-large-v1
This is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
Parameters355M
Context514
Weights12.4 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads643.7k
Runs On
What it takes to serve all-roberta-large-v1 (355M 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 | 0.7 GB | 0.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.4 GB | 0.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 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.
SAVRN's Notes on all-roberta-large-v1
Nine tenths of a gigabyte. That is the memory this embedding model needs at 16-bit, with 0.7 GB of weights, to turn sentences and paragraphs into 1,024-dimensional vectors for clustering and semantic search. The cheapest listed setup is one MI300X with 192 GB at $1.85 an hour on demand, so the card is barely awake and this sits beside whatever else the GPU is doing. The 514-token context is the real constraint: longer text gets chunked first.
Apache 2.0 allows commercial use, modification and redistribution as long as the license and copyright notices travel with the files. Two checks before committing. The repository is 12.4 GB across 29 files because it ships safetensors, ONNX, OpenVINO and PyTorch copies, so pull only the format your runtime loads. And the five papers it cites describe conversational, question-answering and summarization datasets, a fair guide to what it was trained on.
Model Card
By Sentence Transformers, published under apache-2.0, revision cf74d8acd4f1.
This is a sentence-transformers model: It maps sentences & paragraphs to a 1024 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/all-roberta-large-v1')
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
- RobertaForMaskedLM
- Context length (tokens)
- 514
- Layers
- 24
- Hidden size
- 1,024
- Feed-forward size
- 4,096
- Attention heads
- 16
- Vocabulary size
- 50,265
- Model type
- roberta
Identity and Version
- Repository
- sentence-transformers/all-roberta-large-v1
- Publisher
- Sentence Transformers
- Task
- Sentence similarity
- Modality
- Text
- Library
- sentence-transformers
- Parameters
- 355M parameters
- Languages
- en
- Revision
- cf74d8acd4f198de950bf004b262e6accfed5d2c
- First published
- 2022-03-02
- Last updated
- 2025-03-06
Files and Weights
29 files, 12.4 GB in total. The weights are 13 files totalling 12.4 GB in bin, onnx, safetensors.
Weights13 files · 12.4 GB
Configuration8 files · 30.4 KB
Tokenizer4 files · 2.6 MB
Documentation1 file · 9.7 KB
Other2 files · 2.2 MB
Repository1 file · 791 B
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.4 GB | 8d01238e458e |
| onnx/model.onnx | Weights | 1.4 GB | 6f2d93448ed4 |
| onnx/model_O1.onnx | Weights | 1.4 GB | 8c64ffe77708 |
| onnx/model_O2.onnx | Weights | 1.4 GB | 4d2deab7bf2d |
| onnx/model_O3.onnx | Weights | 1.4 GB | 8f189be6603d |
| onnx/model_O4.onnx | Weights | 708.7 MB | 9ee3121f8d86 |
| onnx/model_qint8_arm64.onnx | Weights | 357.3 MB | 3a7e3e4f09df |
| onnx/model_qint8_avx512.onnx | Weights | 357.3 MB | 3a7e3e4f09df |
| onnx/model_qint8_avx512_vnni.onnx | Weights | 357.3 MB | 3a7e3e4f09df |
| onnx/model_quint8_avx2.onnx | Weights | 357.6 MB | 2630f3d1c3e5 |
| openvino/openvino_model.bin | Weights | 1.4 GB | 196b4dc8b44e |
| openvino/openvino_model_qint8_quantized.bin | Weights | 357.1 MB | 4c82375dd327 |
| pytorch_model.bin | Weights | 1.4 GB | 29bb8f3e407e |
| 1_Pooling/config.json | Configuration | 191 B | — |
| config.json | Configuration | 650 B | — |
| config_sentence_transformers.json | Configuration | 116 B | — |
| data_config.json | Configuration | 15.7 KB | — |
| modules.json | Configuration | 349 B | — |
| sentence_bert_config.json | Configuration | 53 B | — |
| special_tokens_map.json | Configuration | 239 B | — |
| train_script.py | Configuration | 13.1 KB | — |
| README.md | Documentation | 9.7 KB | — |
| openvino/openvino_model.xml | Other | 798.7 KB | — |
| openvino/openvino_model_qint8_quantized.xml | Other | 1.4 MB | — |
| .gitattributes | Repository | 791 B | — |
| merges.txt | Tokenizer | 456.4 KB | — |
| tokenizer.json | Tokenizer | 1.4 MB | — |
| tokenizer_config.json | Tokenizer | 328 B | — |
| vocab.json | Tokenizer | 798.3 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 12.4 GB
Download from Sentence Transformers
Released by Sentence Transformers through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:1704.05179
- Described by arXiv:1810.09305
- Described by arXiv:1904.06472
- Described by arXiv:2102.07033
- Described by arXiv:2104.08727
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 12.4 GB |
| 16-bit | 0.7 GB |
| 8-bit | 0.4 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About all-roberta-large-v1
How much GPU memory does all-roberta-large-v1 need?
About 0.9 GB at 16-bit and 0.2 GB at 4-bit: the weights (355M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run all-roberta-large-v1 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 all-roberta-large-v1 commercially?
Yes. all-roberta-large-v1 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 all-roberta-large-v1'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 1024 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…
Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022 This model has 24 layers and the embedding size is 1024. Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset. Please refer to our paper at https://arxiv.org/pdf/2212.03533.pdf. Check out unilm/e5 to reproduce evaluation results on the BEIR and MTEB benchmark. Below is an example for usage with sentencetransformers. Package requirements pip install sentencetransformers~=2.2.2 1. Do I need to add the prefix "query: " and "passage: " to input texts? Yes, this is how the model is trained, otherwise you will see a performance degradation.…
General Text Embeddings (GTE) model. Towards General Text Embeddings with Multi-stage Contrastive Learning The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large, GTE-base, and GTE-small. The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including information retrieval, semantic textual similarity, text reranking, etc. We compared the performance of the GTE models with other popular text embedding models on the MTEB…
The gte-multilingual-base model is the latest in the GTE (General Text Embedding) family of models, featuring several key attributes: Paper: mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval - It is recommended to install xformers and enable unpadding for acceleration, refer to enable-unpadding-and-xformers. - How to use with TEI: refs/pr/7 Usage via docker and infinity, MIT Licensed. Usage via Docker and Text Embeddings Inference (TEI): Then you can send requests to the deployed API via the OpenAI-compatible v1/embeddings route (more information about the OpenAI Embeddings API): We validated the performance of the gte-multilingual-base…
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.…