SAVRN
Search Contact SAVRN

Open-weight model · Fill mask

xlm-roberta-base

by Facebook AI community FacebookAI/xlm-roberta-base

XLM-RoBERTa model pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. It was introduced in the paper Unsupervised Cross-lingual Representation Learning at Scale by Conneau et al. and first released in this repository.

Parameters279M
Context514
Weights6.3 GB
Licensemit
AccessOpen weights
Monthly Downloads21.5M

Runs On

What it takes to serve xlm-roberta-base (279M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso 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.

SAVRN's Notes on xlm-roberta-base

Fill-mask work across 100 languages is where this model earns its place, and the memory math barely registers. At 16-bit the weights are 0.6 GB and the run needs 0.7 GB; the cheapest setup in our table is one MI300X with 192 GB at $1.85 an hour on-demand, leaving nearly all of that card idle. At 8-bit the need is 0.3 GB. With 279M parameters over 12 layers, it fits anywhere a few hundred megabytes of accelerator memory are free.

MIT terms permit commercial use, modification and redistribution; the one obligation is keeping the copyright and permission notices with the files. Check two things before committing: the 514-token context caps each input, and the 6.35 GB download spans 11 files in five formats, so you need only a fraction of it. The page lists no reported evaluations and no host prices, and the last update was February 2024.

SAVRN Research, 2026-09-18

Model Card

By Facebook AI community, published under mit, revision e73636d4f797.

XLM-RoBERTa (base-sized model)

XLM-RoBERTa model pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. It was introduced in the paper Unsupervised Cross-lingual Representation Learning at Scale by Conneau et al. and first released in this repository.

Disclaimer: The team releasing XLM-RoBERTa did not write a model card for this model so this model card has been written by the Hugging Face team.

Model description

XLM-RoBERTa is a multilingual version of RoBERTa. It is pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages.

RoBERTa is a transformers model pretrained on a large corpus in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts.

Read the full model card (579 words)

Configuration

Architecture
XLMRobertaForMaskedLM
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
FacebookAI/xlm-roberta-base
Publisher
Facebook AI community
Task
Fill mask
Modality
Text
Library
transformers
Parameters
279M parameters
Languages
af, am, ar, as, az, be, bg, bn
Revision
e73636d4f797dec63c3081bb6ed5c7b0bb3f2089
First published
2022-03-02
Last updated
2024-02-19

Files and Weights

11 files, 6.4 GB in total. The weights are 5 files totalling 6.3 GB in bin, h5, msgpack, onnx, safetensors.

Weights5 files · 6.3 GB
Configuration1 file · 615 B
Tokenizer2 files · 9.1 MB
Documentation1 file · 5.2 KB
Other1 file · 5.1 MB
Repository1 file · 445 B
Every file
FileTypeSizeSHA-256
flax_model.msgpackWeights1.1 GB 311b6941e021
model.onnxWeights1.9 GB a76bfe6a405f
model.safetensorsWeights1.1 GB 6fd4797bc397
pytorch_model.binWeights1.1 GB 9d83baaafea9
tf_model.h5Weights1.1 GB d1232fb4018a
config.jsonConfiguration615 B —
README.mdDocumentation5.2 KB —
sentencepiece.bpe.modelOther5.1 MB —
.gitattributesRepository445 B —
tokenizer.jsonTokenizer9.1 MB —
tokenizer_config.jsonTokenizer25 B —

License and Download

License
mit
Access
Open weights, no gate
Download size
6.3 GB
Download from Facebook AI community

Released by Facebook AI community through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published6.3 GB
16-bit0.6 GB
8-bit0.3 GB
4-bit0.1 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Built on This Model

Compare xlm-roberta-base

Questions About xlm-roberta-base

How much GPU memory does xlm-roberta-base need?

About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (279M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run xlm-roberta-base 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 xlm-roberta-base commercially?

Yes. xlm-roberta-base is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.

What is xlm-roberta-base's context length?

514 tokens, from the maximum position embeddings in its published configuration.

Similar Models

This is a Japanese DeBERTa V2 large model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR. This model is trained with character-level tokenization and whole word masking. You can use this model for masked language modeling as follows: You can also fine-tune this model on downstream tasks. There is no need to tokenize texts in advance, and you can give raw texts to the tokenizer. The texts are tokenized into character-level tokens by sentencepiece. We used the following corpora for pre-training: - Japanese Wikipedia (as of 20221020, 3.2GB, 27M sentences, 1.3M documents) - Japanese portion of CC-100 (85GB, 619M sentences, 66M documents)…

Open weights cc-by-sa-4.0 330M parameters 512 tokens transformers
View model

Model · Fill mask

bert-large-uncased

BERT community

Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is uncased: it does not make a difference between english and English. Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by the Hugging Face team. BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from…

Open weights apache-2.0 336M parameters 512 tokens transformers
View model

Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is case-sensitive: it makes a difference between english and English. Disclaimer: The team releasing RoBERTa did not write a model card for this model so this model card has been written by the Hugging Face team. RoBERTa is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels…

Open weights mit 355M parameters 514 tokens transformers
View model

Pretrained model on the top 104 languages with the largest Wikipedia using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is case sensitive: it makes a difference between english and English. Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by the Hugging Face team. BERT is a transformers model pretrained on a large corpus of multilingual data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to…

Open weights apache-2.0 179M parameters 512 tokens transformers
View model

Pretrained model on the top 102 languages with the largest Wikipedia using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is uncased: it does not make a difference between english and English. Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by the Hugging Face team. BERT is a transformers model pretrained on a large corpus of multilingual data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process…

Open weights apache-2.0 168M parameters 512 tokens transformers
View model

Model · Fill mask

ModernBERT-large

Answer.AI

ModernBERT is a modernized bidirectional encoder-only Transformer model (BERT-style) pre-trained on 2 trillion tokens of English and code data with a native context length of up to 8,192 tokens. ModernBERT leverages recent architectural improvements such as: - Rotary Positional Embeddings (RoPE) for long-context support. - Local-Global Alternating Attention for efficiency on long inputs. - Unpadding and Flash Attention for efficient inference. ModernBERT’s native long context length makes it ideal for tasks that require processing long documents, such as retrieval, classification, and semantic search within large corpora. The model was trained on a large corpus of text and code, making it…

Open weights apache-2.0 396M parameters 8,192 tokens transformers
View model