PortBERT_base safetensors download (504 MB) | Hugging Bay

Q: What is this model?

PortBERT/PortBERT_base is an open-weights language model for masked-language modeling published by PortBERT, added to Hugging Bay Jun 30, 2026. Model from Hugging Face for fill mask: PortBERT/PortBERT_base · pytorch

Q: Can I use it commercially?

It is released under the mit license. Commercial use is allowed. Permissive open license: commercial use, modification, and redistribution are permitted.

Q: How big is it?

Hosted here: 5 files, 505.7 MB. Full repo upstream: 1.01 GB. The recommended download, model.safetensors, is 504.2 MB.

Q: What can I download here?

Hosted here: 5 files, 505.7 MB. Full repo upstream: 1.01 GB. The original release is at https://huggingface.co/PortBERT/PortBERT_base.

Q: File pattern scans

Automated file-pattern scans flagged nothing; not a safety guarantee. 5 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-portbert-portbert-base/safety on Hugging Bay.

Q: Will PortBERT/PortBERT_base run on my computer?

We can’t check the fit; we don’t know your machine. We don’t have your machine’s specs, so no check ran and no verdict is shown. Answer two quick questions and we’ll estimate, from the memory you tell us, whether it fits your machine. Or skip it; you can still download; fit isn’t checked.

PortBERT

PortBERT_base

PortBERT/PortBERT_base

Model details

masked-language modelingLicense: mitSHA-256 recorded for 6 of 7 filessafetensors · BIN

Content controls: not assessed.

The catalog lists this model for filling in missing words in text. Catalog sources: license, cardMetadata.license, task, cardMetadata.pipelineTag.

View as JSON →

Your next step

Use it from code

This Python snippet downloads the selected file. Running the model needs its own library and setup.

from urllib.request import urlretrieve

urlretrieve(
    "https://huggingbay.xyz/api/downloads/hf-model-portbert-portbert-base/model.safetensors",
    "model.safetensors",
)

Other ways

This file cannot open in the app. The app supports one GGUF file at a time.

See app requirements

5 hosted of 7 listed · Hashes recorded. Date not recorded.

Selected downloadmodel.safetensors504 MB · 1 file Download · 504 MB (1 file)

Open-file help

Content controls: not assessed.

Check your download →

Compare your file’s SHA-256 with the recorded hash.

5 hosted of 7 listed

Hashes recorded. Date not recorded.

File	Size	SHA-256	Source	Download
Weights
`model.safetensors` Default	504.2 MB	`c4bf38cc…98eece0d` `c4bf38cc7a0978a7d98c2861ae6a3fb9e4bb929d2e36d2d4bfd4fc4e98eece0d`	Hosted	Download
`pytorch_model.bin`	504.2 MB	`972c768f…d35914d3` `972c768f05bc3e1606c8b46f97b14b8ae8c36fcaef4ff343f1c1aadbd35914d3`	Upstream only	File metadata
Tokenizer & config
`config.json`	637 bytes	`5d3e059c…2fd910f1` `5d3e059cca438df27a6b8aa554ca1c39ff72d4cc80724979c79dbf7c2fd910f1`	Hosted	Download
`merges.txt`	522.9 KB	`5d43d6cb…c5031d10` `5d43d6cb446b304b9e2074c6bb60575ad08d5d75bf1793fbbeab8160c5031d10`	Hosted	Download
`vocab.json`	980.9 KB	`20655ffb…994acab3` `20655ffbca0e4e400f8612debe065197dbfab9e4c1a52cab5a50a6b0994acab3`	Hosted	Download
Docs
`.gitattributes`	1.52 KB	—	Upstream only	File metadata
`README.md`	6.53 KB	`cabf01a3…b3ed9c50` `cabf01a394a5916f6ec1bd72bcc09d1c1646e039821055913371ce37b3ed9c50`	Hosted	Download

Check a download

In the folder where you saved model.safetensors, run:

macOS

shasum -a 256 -- 'model.safetensors'

Linux

sha256sum -- 'model.safetensors'

Windows

Get-FileHash -LiteralPath 'model.safetensors' -Algorithm SHA256

Compare the result with the recorded SHA-256.

PortBERT_base

Check a download

Cookies