This is the pretrained model presented in SecBERT: A Pretrained Language Model for Cyber Security Text, which is a BERT model trained on cyber security text. The training corpus was papers taken from SecBERT has its own wordpiece vocabulary (secvocab) that's built to best match the training corpus. We trained SecBERT and SecRoBERTa versions. We proposed to build language model which work on cyber security text, as result, it can improve downstream tasks (NER, Text Classification, Semantic Understand, Q&A) in Cyber Security Domain. First, as below shows Fill-Mask pipeline in Google Bert, AllenAI SciBert and our SecBERT. The original repo can be found here.
Open-weight model · Fill mask
distilroberta-base
by DistilBERT community distilbert/distilroberta-base
This model is a distilled version of the RoBERTa-base model. It follows the same training procedure as DistilBERT. The code for the distillation process can be found here.
Parameters83M
Context514
Weights2.0 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads1.4M
Runs On
What it takes to serve distilroberta-base (83M 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 | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 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 distilroberta-base
Two tenths of a gigabyte. That is the memory this masked-language model needs at 16-bit, and it settles the hardware question. The cheapest setup on our Index is one MI300X with 192 GB at $1.85 an hour on-demand, which leaves most of that card idle, so it belongs on a GPU you already run, beside other small models, or as the base for a fine-tuned classifier, which the publisher says is its main purpose. At 6 layers and 83M parameters against 125M for RoBERTa-base, a fine-tuning run is a smaller job too.
Apache 2.0 allows commercial use, modification and redistribution and carries a patent grant, so a fine-tuned derivative can ship in a product with the notices attached. Check the 514-token context, which means long documents get chunked, and note the openwebtext training corpus and the 2024-02-19 last update. Weights come as safetensors, pytorch, jax, rust and tf.
Model Card
By DistilBERT community, published under apache-2.0, revision fb53ab880285.
Model Card for DistilRoBERTa base
Table of Contents
- Model Details
- Uses
- Bias, Risks, and Limitations
- Training Details
- Evaluation
- Environmental Impact
- Citation
- How To Get Started With the Model
Model Details
Model Description
This model is a distilled version of the RoBERTa-base model. It follows the same training procedure as DistilBERT. The code for the distillation process can be found here. This model is case-sensitive: it makes a difference between english and English.
The model has 6 layers, 768 dimension and 12 heads, totalizing 82M parameters (compared to 125M parameters for RoBERTa-base). On average DistilRoBERTa is twice as fast as Roberta-base.
We encourage users of this model card to check out the RoBERTa-base model card to learn more about usage, limitations and potential biases.
Configuration
- Architecture
- RobertaForMaskedLM
- Context length (tokens)
- 514
- Layers
- 6
- Hidden size
- 768
- Feed-forward size
- 3,072
- Attention heads
- 12
- Vocabulary size
- 50,265
- Model type
- roberta
Identity and Version
- Repository
- distilbert/distilroberta-base
- Publisher
- DistilBERT community
- Task
- Fill mask
- Modality
- Text
- Library
- transformers
- Parameters
- 83M parameters
- Languages
- en
- Revision
- fb53ab8802853c8e4fbdbcd0529f21fc6f459b2b
- First published
- 2022-03-02
- Last updated
- 2024-02-19
Files and Weights
13 files, 2.0 GB in total. The weights are 5 files totalling 2.0 GB in bin, h5, msgpack, ot, safetensors.
Weights5 files · 2.0 GB
Configuration1 file · 480 B
Tokenizer4 files · 2.7 MB
Documentation1 file · 7.5 KB
Other1 file · 603.3 KB
Repository1 file · 445 B
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| flax_model.msgpack | Weights | 328.7 MB | 4da82a2cd90e |
| model.safetensors | Weights | 331.1 MB | 2b11ca9cf3d2 |
| pytorch_model.bin | Weights | 331.1 MB | ec1ed6ff4c97 |
| rust_model.ot | Weights | 485.5 MB | a5bc30eee4d3 |
| tf_model.h5 | Weights | 487.2 MB | 92d6207eedd0 |
| config.json | Configuration | 480 B | — |
| README.md | Documentation | 7.5 KB | — |
| dict.txt | Other | 603.3 KB | — |
| .gitattributes | Repository | 445 B | — |
| merges.txt | Tokenizer | 456.3 KB | — |
| tokenizer.json | Tokenizer | 1.4 MB | — |
| tokenizer_config.json | Tokenizer | 25 B | — |
| vocab.json | Tokenizer | 898.8 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 2.0 GB
Download from DistilBERT community
Released by DistilBERT community through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:1910.01108
- Described by arXiv:1910.09700
- Trained on (disclosed) openwebtext
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 2.0 GB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Built on This Model
- Quantized fromnli-distilroberta-base
- Derived fromnli-distilroberta-base
Compare distilroberta-base
Questions About distilroberta-base
How much GPU memory does distilroberta-base need?
About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (83M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run distilroberta-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 distilroberta-base commercially?
Yes. distilroberta-base 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 distilroberta-base's context length?
514 tokens, from the maximum position embeddings in its published configuration.
Similar Models
This model is a distilled version of the BERT base model. It was introduced in this paper. The code for the distillation process can be found here. This model is uncased: it does not make a difference between english and English. DistilBERT is a transformers model, smaller and faster than BERT, which was pretrained on the same corpus in a self-supervised fashion, using the BERT base model as a teacher. 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 using the BERT base model. More precisely, it was pretrained…
This model has been pre-trained for Chinese, training and random input masking has been applied independently to word pieces (as in the original BERT paper). This model can be used for masked language modeling CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes. Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). typevocabsize: 2 vocabsize: 21128 numhiddenlayers: 12
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 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…
Eval data: Conll03 (NER), GermEval14 (NER), GermEval18 (Classification), GNAD (Classification) Update April 3rd, 2020: we updated the vocabulary file on deepset's s3 to conform with the default tokenization of punctuation tokens. For details see the related FARM issue. If you want to use the old vocab we have also uploaded a "deepset/bert-base-german-cased-oldvocab" model. - We trained using Google's Tensorflow code on a single cloud TPU v2 with standard settings. - We trained 810k steps with a batch size of 1024 for sequence length 128 and 30k steps with sequence length 512. Training took about 9 days. - As training data we used the latest German Wikipedia dump (6GB of raw txt files), the…
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 labeling 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…