SAVRN
Search Contact SAVRN

Open-weight model · Fill mask

roberta-large

by Facebook AI community FacebookAI/roberta-large

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.

Parameters355M
Context514
Weights7.5 GB
Licensemit
AccessOpen weights
Monthly Downloads6.5M

Runs On

What it takes to serve roberta-large (355M 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 0.7 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 roberta-large

Loaded at 16-bit, roberta-large needs 0.9 GB of memory for 0.7 GB of weights, and the cheapest setup the SAVRN Index prices for it is one MI300X with 192 GB at $1.85 per hour on demand. Two hundred copies would fit on that card, so the hardware question is not whether it fits but how many instances you stack per accelerator. The job is fill mask on case-sensitive English text: 355M parameters across 24 layers predict a masked token.

MIT is as light as a license gets: commercial use, modification and redistribution, with the copyright and permission notices kept in the package. Context is 514 tokens, so longer documents get chunked first. The 7.5 GB of files spans five formats, safetensors, ONNX, PyTorch, JAX and TensorFlow; pull the one your serving stack loads. Pretraining data was BookCorpus and Wikipedia, English only; the method is in arXiv:1907.11692.

SAVRN Research, 2026-09-18

Model Card

By Facebook AI community, published under mit, revision 722cf37b1afa.

RoBERTa large 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.

Model description

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 from those texts.

Read the full model card (1,115 words)

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
FacebookAI/roberta-large
Publisher
Facebook AI community
Task
Fill mask
Modality
Text
Library
transformers
Parameters
355M parameters
Languages
en
Revision
722cf37b1afa9454edce342e7895e588b6ff1d59
First published
2022-03-02
Last updated
2024-02-19

Files and Weights

12 files, 7.5 GB in total. The weights are 5 files totalling 7.5 GB in bin, h5, msgpack, onnx, safetensors.

Weights5 files · 7.5 GB
Configuration1 file · 482 B
Tokenizer4 files · 2.7 MB
Documentation1 file · 9.3 KB
Repository1 file · 445 B
Every file
FileTypeSizeSHA-256
flax_model.msgpackWeights1.4 GB 267290826382
model.onnxWeights1.6 GB cd19cb4d52d5
model.safetensorsWeights1.4 GB 047c85f0b962
pytorch_model.binWeights1.4 GB 36a10a8b694f
tf_model.h5Weights1.6 GB e5a6c9c1643e
config.jsonConfiguration482 B —
README.mdDocumentation9.3 KB —
.gitattributesRepository445 B —
merges.txtTokenizer456.3 KB —
tokenizer.jsonTokenizer1.4 MB —
tokenizer_config.jsonTokenizer25 B —
vocab.jsonTokenizer898.8 KB —

License and Download

License
mit
Access
Open weights, no gate
Download size
7.5 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 published7.5 GB
16-bit0.7 GB
8-bit0.4 GB
4-bit0.2 GB

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

Built on This Model

Compare roberta-large

Questions About roberta-large

How much GPU memory does roberta-large 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 roberta-large 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 roberta-large commercially?

Yes. roberta-large 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 roberta-large's context length?

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

Similar Models

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

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

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

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. 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…

Open weights mit 279M 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