alt.freeweights.vision / stsb-roberta-large
From: cross-encoder <huggingface.co/cross-encoder>Newsgroups: alt.freeweights.visionSubject:

stsb-roberta-large

Date: 2026-11-15Commit: 2b12c2cSigned: 2DC28CC7B26A283B ✓

Text ranking model with 355M parameters. Onnx and openvino and safetensors weights, 13.9 GB in all. Published by cross-encoder under Apache-2.0.

355M params13.9GBstsb-roberta-largeonnx openvino safetensorspermissive
FactsParams355MSize13.9 GBFormatsonnx, openvino, safetensorsTasktext rankingLicenseApache-2.0From sourcepermissive
$ fw get cross-encoder/stsb-roberta-large
# manifest sha256 0de2e67d5697… · 13.9 GB · 25 files
$ fw verify ./stsb-roberta-large cross-encoder/stsb-roberta-large
From sourceHosted (signed)cross-encoder/stsb-roberta-largeLast check: 2026-11-15 04:37 UTC

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of roberta-large.

Overview

Size
13.9 GB
Weights
1.42 GB (safetensors)
Parameters
355M
Formats
onnx, openvino, safetensors
Task
text ranking
License
Apache-2.0 (permissive)
Files
25, each with a sha256
Publisher
cross-encoder
Added
2026-11-15
Section
alt.freeweights.vision
Lineage

Original release from the publisher.

Base model: FacebookAI/roberta-large

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 04:37 UTCpassed

Model card

From the publisher at commit 2b12c2c. Shown as plain text with links; images open at the publisher.

Cross-Encoder for Semantic Textual Similarity#

This model was trained using SentenceTransformers Cross-Encoder class.

Training Data#

This model was trained on the STS benchmark dataset. The model will predict a score between 0 and 1 how for the semantic similarity of two sentences.

Usage and Performance#

Pre-trained models can be used like this:

from sentence_transformers import CrossEncoder

model = CrossEncoder('cross-encoder/stsb-roberta-large')
scores = model.predict([('Sentence 1', 'Sentence 2'), ('Sentence 3', 'Sentence 4')])

The model will predict scores for the pairs ('Sentence 1', 'Sentence 2') and ('Sentence 3', 'Sentence 4').

You can use this model also without sentence_transformers and by just using Transformers AutoModel class

Files

25 files · 13.9 GBWeights 1.42 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 25 files with their sha256
FileSizesha256
.gitattributes445 B98c91dabef4df27b2fc7c8454d220aba47476f73593cbd034d961fe4927304c1
CECorrelationEvaluator_sts-dev_results.csv223 Bfa3c0fdbe4260209e7ac0222eb78bfb9693fca60a9aecb3e3ea7426b1975c1b8
README.md1.14 KBbe18933aed9576e9820e675a4b5272bd1a0fa4bf62468c187a2ac0b77b10ba6d
config.json629 Bbbb09aa22781fd4b7357c209b93266022fadba91af9e81ba7820f6a5af6dfc9d
flax_model.msgpack1.42 GB646b3fe48a91743c4bfd18fa129ee4278573dd6634324e64baa6d8b7104c11ef
merges.txt456 KB1ce1664773c50f3e0cc8842619a93edc4624525b728b188a9e0be33b7726adc5
model.safetensors1.42 GB613af2a4f0a5deb23b07c71649c50a1e1cd76470697f3104e11a7859d80ca832
onnx/model.onnx1.42 GBb26274ff04219b5bcc8e09202205201d0e9bfb8905d02c5cb9d2e133f229d55c
onnx/model_O1.onnx1.42 GBbee5a8a1f6db9ffb7fb0a5d8fe0c0cb8c4e204dfa907a0beac4884dc70352e5e
onnx/model_O2.onnx1.42 GB2cdde759506204305ec7426647f8c2b16d6c7ea5ecfe23b1f573a634c96dee43
onnx/model_O3.onnx1.42 GB40fd080a90f9195f94c8b89b1a83798ae5972408acb447b159931f099d5d27e2
onnx/model_O4.onnx711 MB7a03bde92ae3ec5d11fd57e9f63210d7f1e198800b55ea6e5b39ad93530e68f4
onnx/model_qint8_arm64.onnx359 MBe015610e2454296350ebd3b1c0e12646075066734c628c40648fc6796073d9d7
onnx/model_qint8_avx512.onnx359 MBe015610e2454296350ebd3b1c0e12646075066734c628c40648fc6796073d9d7
onnx/model_qint8_avx512_vnni.onnx359 MBe015610e2454296350ebd3b1c0e12646075066734c628c40648fc6796073d9d7
onnx/model_quint8_avx2.onnx359 MBc1daad07e40faf372bbca890456a5b4b1a3422223aaea916c4c2ba961c42a843
openvino/openvino_model.bin1.42 GBcaeed3fdd51245b064b8ba14dfa5582083b5379ddb1b4d47568e34dbb9e5d11d
openvino/openvino_model.xml751 KB6e351be6ca5f2cc3301dfc701e179798d90904696eb0349b94ef3aedb01db031
openvino/openvino_model_qint8_quantized.bin358 MB9592b5aeb6e340c9648e0769a84cd2a0d9d4c60dc5b9646fa500b5838f4f7dc6
openvino/openvino_model_qint8_quantized.xml1.38 MBbaabb684af987460a70da4bf09ab6781ed624ed63cbda23e45ed44295571608d
pytorch_model.bin1.42 GB03023f7dcd714c15ff27d534432a80d3bff78c9b50778a44b10585ef5fa7fd25
special_tokens_map.json1.01 KB75cbec71553267dadc77a583ef15122c2aa7422eb6635acc72a184a413f17c1c
tokenizer.json3.56 MB2bb1a22cfbe25b8e5a232b7fc4d7fc5073923b45724a5f813b00811bb6620f66
tokenizer_config.json1.33 KBfe09e6fe347cc94002f77bec394efa02db0ac151393f940d0d854af765e8b165
vocab.json798 KBed19656ea1707df69134c4af35c8ceda2cc9860bf2c3495026153a133670ab5e
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
2b12c2c008 pinned now2026-11-15 04:37 UTC25 files · 13.9 GB

Use it

$ fw get cross-encoder/stsb-roberta-large
# manifest sha256 0de2e67d5697… · 13.9 GB · 25 files
$ fw verify ./stsb-roberta-large cross-encoder/stsb-roberta-large
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/cross-encoder/stsb-roberta-large.json --dir ./stsb-roberta-large $ python3 fw.py verify ./stsb-roberta-large ./cross-encoder__stsb-roberta-large.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download cross-encoder/stsb-roberta-large --revision 2b12c2c0088918e76151fd5937b7bba986ef1f98 --local-dir ./stsb-roberta-large

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
be18933aed9576e9820e675a4b5272bd1a0fa4bf62468c187a2ac0b77b10ba6d
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: cross-encoder <huggingface.co/cross-encoder>Newsgroups: alt.freeweights.visionSubject: stsb-roberta-largeDate: 2026-11-15Commit: 2b12c2cSigned: 2DC28CC7B26A283B ✓
Upstream
cross-encoder/stsb-roberta-large
Pinned commit
2b12c2c0088918e76151fd5937b7bba986ef1f98
Manifest
stsb-roberta-large.json · .minisig
Manifest sha256
0de2e67d569714623aae2c2fa1e4e84ed02ca133d9360856904234c8064a820f
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:37 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/cross-encoder/stsb-roberta-large.json $ curl -O https://freeweights.allternit.com/manifests/cross-encoder/stsb-roberta-large.json.minisig $ minisign -Vm stsb-roberta-large.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

FacebookAI/roberta-large · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download cross-encoder/stsb-roberta-large
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. stsb-roberta-large.json. Provenance. Takedown history: none.
From: dima806 <huggingface.co/dima806>Subject: ai_vs_real_image_detection
From: legekka <huggingface.co/legekka>Subject: AI-Anime-Image-Detector-ViT
From: onnx-community <huggingface.co/onnx-community>Subject: AI-Anime-Image-Detector-ViT-ONNX
From: AICodexLab <huggingface.co/AICodexLab>Subject: answerdotai-ModernBERT-base-ai-detector
From: onnx-community <huggingface.co/onnx-community>Subject: answerdotai-ModernBERT-base-ai-detector-ONNX
From: onnx-community <huggingface.co/onnx-community>Subject: bart-large-cnn-ONNX