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.
hEVO-base-o is a model for fill mask from Mulin Lab (access requested at publisher). It has 87M parameters. At 16-bit it needs about 0.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 3 downloads a month.
hEVO-base-o is the base checkpoint in the hEvo public-data model family. It was independently pretrained on 1000 Genomes Project and Human Genome Diversity Project sequences using self-supervised masked language modeling.
Parameters87M
Context—
Weights174.2 MB
License—
AccessAccess requested at publisher
Monthly Downloads3
Runs On
What it takes to serve hEVO-base-o (87M 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 | 0.1 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 Oct 25, 2026.
hEVO-base-o on every accelerator the SAVRN Index prices, at every precision
Model Card
hEVO-base-o is the base checkpoint in the hEvo public-data model family. It was independently pretrained on 1000 Genomes Project and Human Genome Diversity Project sequences using self-supervised masked language modeling. The checkpoint provenance records no target benchmark label supervision. Use a Python environment with PyTorch and the checkpoint's tested Transformers version: Access is gated for peer reviewers and requires manual approval by MulinLab. Sign in to Hugging Face, submit an access request on this page, and wait for approval. After approval, run hf auth login with your own read token; token=True below uses your locally stored credential. The model and tokenizer load…
Excerpt from the card by Mulin Lab.
Identity and Version
- Repository
- MulinLab/hEVO-base-o
- Publisher
- Mulin Lab
- Task
- Fill mask
- Modality
- Text
- Library
- transformers
- Parameters
- 87M parameters
- Languages
- Not stated by the source
- Revision
- bd232444555c44779d56d49fe402a7281a0405f6
- First published
- 2026-10-14
- Last updated
- 2026-10-19
Files and Weights
14 files, 175.9 MB in total. The weights are 1 file totalling 174.2 MB in safetensors.
Weights1 file · 174.2 MB
Configuration6 files · 40.9 KB
Tokenizer3 files · 1.4 KB
Documentation1 file · 10.2 KB
Other2 files · 1.6 MB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 174.2 MB | — |
| config.json | Configuration | 1.6 KB | — |
| data.py | Configuration | 13.7 KB | — |
| model.py | Configuration | 23.2 KB | — |
| provenance.json | Configuration | 572 B | — |
| release_manifest.json | Configuration | 1.7 KB | — |
| special_tokens_map.json | Configuration | 125 B | — |
| README.md | Documentation | 10.2 KB | — |
| assets/header.png | Other | 1.6 MB | — |
| requirements.txt | Other | 61 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer_config.json | Tokenizer | 1.3 KB | — |
| vocab.json | Tokenizer | 101 B | — |
| vocab.txt | Tokenizer | 41 B | — |
License and Download
- License
- Not stated by the source
- Access
- Access requested at publisher
- Download size
- 174.2 MB
Request access from Mulin Lab
Mulin Lab grants access through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 174.2 MB |
| 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.
Questions About hEVO-base-o
How much GPU memory does hEVO-base-o need?
About 0.2 GB at 16-bit and 0.1 GB at 4-bit: the weights (87M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run hEVO-base-o 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.
Similar Models
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. 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. You can use the raw model for masked language modeling, but it's mostly intended to be fine-tuned on a downstream task. See the model hub to look for fine-tuned versions on a task that interests you.…
This model is a fine-tuned version of distilbert/distilroberta-base on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 2e-05 - trainbatchsize: 8 - evalbatchsize: 8 - lrschedulertype: linear - numepochs: 3 - Transformers 5.17.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2
This model is a fine-tuned version of distilroberta-base on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 2e-05 - trainbatchsize: 8 - evalbatchsize: 8 - lrschedulertype: linear - numepochs: 3.0 - Transformers 5.18.0 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.23.2
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
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…