roberta-base
FacebookAI/roberta-baseContent controls: not assessed.
Model from Hugging Face for fill mask: FacebookAI/roberta-base · transformers
Model facts
roberta-base is an open-weights language model for masked-language modeling. The primary file is model.safetensors (499 MB). The primary file needs about 2 GB free for the selected file. License: MIT. The SHA-256 prefix is 5bde1d28afb3. The primary Download is available now. No tested run commands for this file yet. Some listed files are available here. The size and hash details refer to the selected file, not every file in the repository. The memory figure is estimated from recorded file size with working room included. The size line uses recorded file bytes when they are present in this model record.
What's included
About this model
External Hugging Face catalog record for FacebookAI/roberta-base. Task: fill mask. Library: transformers. Languages: en. Datasets referenced by card metadata: bookcorpus, wikipedia. Files we host have a published SHA-256.
Quick facts
- Hosted here
- 6 files, 501.5 MB
- Full repo upstream
- 2.82 GB
- Recommended file
- 498.8 MB · model.safetensors
- Languages
- en
- Format
- safetensors · BIN · H5
- Files hosted
- 6 of 11
- Downloads on Hugging Face
- 11,523,486
- File hashes
- Hashes recorded. Date not recorded.
License & source
License: mit
Check the license text and keep the required notices when you use or share the files.
Upstream source →- Task
- masked-language modeling
- Hosted here
- 6 files, 501.5 MB
- Full repo upstream
- 2.82 GB
- Recommended file
- 498.8 MB · model.safetensors
- Files
- 6 hosted of 11 listed
- Download
- Download here (6 hosted files)
- Added to Hugging Bay
- Updated at source
- Source
- FacebookAI/roberta-base
FAQ
What is this model?
FacebookAI/roberta-base is an open-weights language model for masked-language modeling published by FacebookAI, added to Hugging Bay Jun 29, 2026. Model from Hugging Face for fill mask: FacebookAI/roberta-base · transformers
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.
How big is it?
Hosted here: 6 files, 501.5 MB. Full repo upstream: 2.82 GB. The recommended download, model.safetensors, is 498.8 MB.
What can I download here?
Hosted here: 6 files, 501.5 MB. Full repo upstream: 2.82 GB. The original release is at https://huggingface.co/FacebookAI/roberta-base.
File checks and computer fit
File pattern scans
Automated file-pattern scans flagged nothing; not a safety guarantee. 6 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-facebookai-roberta-base/safety on Hugging Bay.
Will FacebookAI/roberta-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.