FacebookAI/xlm-roberta-base License

Skip to main contentHugging Bay

FacebookAI/xlm-roberta-base license and verification status on Hugging Bay. License: mit. Scan: passed.

License: mit
Task: masked-language modeling
Size: 5.9 GB
Files: 0 listed, none hosted here
Download: Not hosted here; download from Hugging Face
Released: Jun 30, 2026
Updated on Hugging Bay: Feb 19, 2024
Source: FacebookAI/xlm-roberta-base

FAQ

What is FacebookAI/xlm-roberta-base?

FacebookAI/xlm-roberta-base is an open-weights language model for masked-language modeling published by FacebookAI, released Jun 30, 2026. Model from Hugging Face for fill mask: FacebookAI/xlm-roberta-base · transformers

What license does FacebookAI/xlm-roberta-base use, and 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 FacebookAI/xlm-roberta-base?

The total download is 5.9 GB.

Where can I download FacebookAI/xlm-roberta-base?

Hugging Bay does not host files for this model. Download it from the original Hugging Face release at https://huggingface.co/FacebookAI/xlm-roberta-base. No file list is recorded; total size: 5.9 GB.

Has FacebookAI/xlm-roberta-base been scanned for unsafe files?

Source scan status: passed. No files are hosted here, so no hosted-file hashes are published. The machine-readable verdict is at /api/artifacts/hf-model-facebookai-xlm-roberta-base/safety on Hugging Bay.

Does FacebookAI/xlm-roberta-base run on an RTX 4090 (24GB)?

FacebookAI/xlm-roberta-base needs ~8.23 GB, which is within the 24 GB on an RTX 4090 (24GB) by memory capacity (~15.77 GB headroom). Computed from stated size and quant, not a runtime guarantee.

Does FacebookAI/xlm-roberta-base run on an RTX 3090 (24GB)?

FacebookAI/xlm-roberta-base needs ~8.23 GB, which is within the 24 GB on an RTX 3090 (24GB) by memory capacity (~15.77 GB headroom). Computed from stated size and quant, not a runtime guarantee.

Does FacebookAI/xlm-roberta-base run on an A100 (80GB)?

FacebookAI/xlm-roberta-base needs ~8.23 GB, which is within the 80 GB on an A100 (80GB) by memory capacity (~71.77 GB headroom). Computed from stated size and quant, not a runtime guarantee.

Does FacebookAI/xlm-roberta-base run on a 16GB laptop (no dedicated GPU)?

FacebookAI/xlm-roberta-base needs ~8.23 GB, which is within the 16 GB on a 16GB laptop (no dedicated GPU) by memory capacity (~7.77 GB headroom). Computed from stated size and quant, not a runtime guarantee.

Does FacebookAI/xlm-roberta-base run on an 8GB laptop (no dedicated GPU)?

FacebookAI/xlm-roberta-base needs ~8.23 GB of memory (weights + KV cache at 8192 tokens); that is more than the 8 GB on an 8GB laptop (no dedicated GPU), so it does not fit. Computed from stated size and quant, not a runtime guarantee.

License

Exact declared identifier: mit

Permissive open license: commercial use, modification, and redistribution are permitted.

Keep every copyright, attribution, license, and NOTICE requirement imposed by the exact license text.

Exact upstream license record

{
  "declaredLicense": "mit",
  "upstreamLicenseRaw": "mit",
  "sourceUrl": "https://huggingface.co/FacebookAI/xlm-roberta-base",
  "upstream": {
    "gated": false,
    "repoId": "FacebookAI/xlm-roberta-base",
    "private": false,
    "repoUrl": "https://huggingface.co/FacebookAI/xlm-roberta-base",
    "disabled": false,
    "provider": "huggingface",
    "repoType": "model",
    "revision": "e73636d4f797dec63c3081bb6ed5c7b0bb3f2089",
    "fetchedAt": "2026-09-21T03:29:40.807Z",
    "importMode": "mirrored-release",
    "licenseRaw": "mit",
    "licenseDeclared": "mit",
    "mirrorLicensePolicy": "permissive"
  }
}

Plain-English license guide Upstream source License and source record

The summary never replaces the exact upstream license text, notices, or machine-readable obligations.

Scan: passed. Removed or disputed files stay out of search, mirrors, and APIs.

Evidence details

Demand: 20M upstream downloads
Trust: Metadata checked 0/100
Trusted download: File inventory only
Run fit: Canonical selected-byte evidence recorded; public obtain path unavailable
Scan status: passed
Executable state: complete-bytes
Evidence timestamp: 2026-08-18T19:56:26.820Z
Declared license: mit
Pipeline: fill-mask
Library: transformers
Task categories: fill-mask
Languages: multilingual, af, am, ar, as, az, be, bg
Paper ids: 1911.02116
File hints: 11 upstream file samples

Public files only. Gated and restricted sources stay gated.