FacebookAI/roberta-base
FacebookAI/roberta-base is a FacebookAI record on this register. The Hugging Face model API lists the pipeline tag as fill-mask. The safetensors index gives an exact parameter count of 124,697,947. Architectural context length (max_position_embeddings) is 514. The listed licence is mit. The Hub repository was created on 2 Mar 2022, which is the release date this register uses.
Primary source: the Hugging Face model card for FacebookAI/roberta-base. Fields below come from that card, the Hub model API, and the repository’s own config.json when those files exist. A field we cannot source is omitted rather than guessed.
| Organisation | FacebookAI |
|---|---|
| ReleasedRepo creation date on Hugging Face | 2 Mar 2022 |
| Last modified | 19 Feb 2024 |
| ParametersExact, from the safetensors index | 125M 124,697,947 |
| Context lengthmax_position_embeddings — architectural maximum, not necessarily served | 514 514 |
| Licence | mit |
| Pipeline / taskpipeline_tag on the Hugging Face model API | fill-mask |
| File formats | safetensors |
| Librarylibrary_name on the Hugging Face model API | transformers |
| Architecture | roberta |
| Layers | 12 |
| Vocabulary | 50,265 |
| DownloadsAt last check | 7.6m |
| Likes | 691 |
| Gated | No |
How to run
Safetensors weights are on the Hugging Face repository. The parameter count on this page came from that index.
The Hugging Face model API lists the library as transformers.
Load it from huggingface.co/FacebookAI/roberta-base. This page does not add install steps that the Hub files do not state.
Agent capabilities
This model publishes no chat template, so there is nothing to inspect. That is not evidence of missing support — many base models and some releases simply ship without one.
Questions this record can answer
- When was roberta-base released?
- The Hugging Face repository was created on 2 Mar 2022, which is the date this register uses.
- How many parameters does roberta-base have?
- The safetensors index gives 124,697,947 parameters, shown here as 125M. That figure is exact, not rounded.
- What is the context length of roberta-base?
- 514 tokens. That is max_position_embeddings from the model's own config.json — the architectural maximum, not necessarily the context a provider serves.
- What licence is roberta-base under?
- The Hub card lists mit.
- Is roberta-base gated?
- No. The Hugging Face model API does not mark this repository as gated.
Where each field came from
- Hugging Face model API — releasedAt, lastModified, downloads, likes, task, license, gated, parameters, libraryName, formats. Checked 18 Oct 2026.
- config.json — contextLength, layers, vocabSize, architecture. Checked 18 Oct 2026.
First recorded 24 Sept 2026, last checked 18 Oct 2026. This record is compiled automatically from the sources above. Where a field is blank, we could not source it and have not guessed. Canonical repository: huggingface.co/FacebookAI/roberta-base.