CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.vision / quora-distilroberta-base
From: cross-encoder <huggingface.co/cross-encoder>Newsgroups: alt.freeweights.visionSubject:

quora-distilroberta-base

Date: 2026-11-15Commit: f62e7a4Signed: 2DC28CC7B26A283B ✓

Text ranking model with 82M parameters. Onnx and openvino and safetensors weights, 3.21 GB in all. Published by cross-encoder under Apache-2.0.

82M params3.21GBquora-distilroberta-baseonnx openvino safetensorspermissive
FactsParams82MSize3.21 GBFormatsonnx, openvino, safetensorsTasktext rankingLicenseApache-2.0From sourcepermissive
$ fw get cross-encoder/quora-distilroberta-base
# manifest sha256 cf894212936b… · 3.21 GB · 25 files
$ fw verify ./quora-distilroberta-base cross-encoder/quora-distilroberta-base
From sourceHosted (signed)cross-encoder/quora-distilroberta-baseLast check: 2026-11-15 04:51 UTC
Get help

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

Quantized of distilroberta-base.

Runs withBentoMLCTranslate2ExLlamaV2LitServeLocalAIOpenVINOText Embeddings InferencetinygradTransformersTriton Inference ServerUltralyticsFine-tune withAccelerateDeepSpeedJAXKerasPyTorch Lightningsd-scriptsSentence TransformersSimpleTunerConvert withCore ML ToolsExecuTorchOliveONNXOptimum QuantoOptimumsafetensorstorchaoEvaluate withMTEBScan withModelScanpicklescanWorks withChromaFAISSFlagEmbeddinghnswlibInfinitykotaemonLightRAGMilvuspgvectorpgvectorscaleQdrantRAGFlowsqlite-vectxtaiTypesenseWeaviate
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
3.21 GB
Weights
328 MB (safetensors)
Parameters
82M
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: distilbert/distilroberta-base

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 04:51 UTCpassed

Model card

From the publisher at commit f62e7a4. Shown as plain text with links; images open at the publisher.

Cross-Encoder for Quora Duplicate Questions Detection#

This model was trained using SentenceTransformers Cross-Encoder class.

Training Data#

This model was trained on the Quora Duplicate Questions dataset. The model will predict a score between 0 and 1 how likely the two given questions are duplicates.

Note: The model is not suitable to estimate the similarity of questions, e.g. the two questions "How to learn Java" and "How to learn Python" will result in a rather low score, as these are not duplicates.

Usage and Performance#

Pre-trained models can be used like this:

from sentence_transformers import CrossEncoder

model = CrossEncoder('cross-encoder/quora-distilroberta-base')
scores = model.predict([('Question 1', 'Question 2'), ('Question 3', 'Question 4')])

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

Files

25 files · 3.21 GBWeights 328 MB (safetensors). Sizes and sha256 from the signed manifest.
Show all 25 files with their sha256
FileSizesha256
.gitattributes445 B98c91dabef4df27b2fc7c8454d220aba47476f73593cbd034d961fe4927304c1
CEBinaryClassificationEvaluator_Quora-dev_results.csv2.07 KBf124060f1878235da9eba76bcb21edc3882760f0cfc7ea4d9b703235a5a6e2af
README.md1.30 KB59baa6da620d95c9045e86a091d84e00074c42ec40c1cc04d4799914ee4fe6b7
config.json607 B4d3d424eb9a2e40b2bc7ae274147f274b031e508de73cdf28e75f759a4360a08
flax_model.msgpack328 MB81ee85c07ec9df3edd54b02c4fc70881ee5e1903d0d1ab0b79e3eb4e876cf816
merges.txt456 KB1ce1664773c50f3e0cc8842619a93edc4624525b728b188a9e0be33b7726adc5
model.safetensors328 MB73fd14ad7d08f3ef30eb25841c8f4ba89e91230f48159279233b37015ccb33fb
onnx/model.onnx329 MB4cc6fc9e972b5074b6cb41e3cc1667347909a8c240b6913d143bb10ec5e5df26
onnx/model_O1.onnx329 MBb111bc4bb35a5bf188201de27033b14a82e55e3dad241541dd051f4e49b329fc
onnx/model_O2.onnx329 MBd16a73b270d98e13a530eb2c48c8aadc1a3a2fcb2c09bb8ce4ab57d70c84356c
onnx/model_O3.onnx329 MB081739b944db5ac3d0f40a2ffbe38289b9261380f6c45d535ca0a2bce370e64f
onnx/model_O4.onnx164 MB9d7bd67835cb0c03f5fd1b394885683e1543bd9c85d93ec13c3b4cba50b88fca
onnx/model_qint8_arm64.onnx82.8 MB845ea205de16c9c7f0587dd29b7e45a8c31f8e1ea2766e69932a28af2bcb8ed5
onnx/model_qint8_avx512.onnx82.8 MB845ea205de16c9c7f0587dd29b7e45a8c31f8e1ea2766e69932a28af2bcb8ed5
onnx/model_qint8_avx512_vnni.onnx82.8 MB845ea205de16c9c7f0587dd29b7e45a8c31f8e1ea2766e69932a28af2bcb8ed5
onnx/model_quint8_avx2.onnx82.8 MB9bab6d0016bcfc2c24c9bc0f747a9a6ceb53f262738ea1df3144aa7a764c1ce5
openvino/openvino_model.bin328 MB0cee454a46a5a2a7a8c9cf648f2aab3e51a038cf8e1550d911c3eedecf6b9e9b
openvino/openvino_model.xml212 KB05e064b824a011f3d4113792a317e619b72fd6f1d7263bfec05f5be8d79d8928
openvino/openvino_model_qint8_quantized.bin82.8 MB9c0dadd29f6adc34563787ddd2e9692a8ac8f9bf0e2b4f89dce0197f649f120c
openvino/openvino_model_qint8_quantized.xml379 KB243a88e5c5a1695260315ff4e1d9e23a9c3335006f2bc7ce9c8c480aef721bd4
pytorch_model.bin329 MBe1642652001f9d60e227169da750327d26d6d37b531f90d79b5cd1516a94b20a
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
f62e7a4b20 pinned now2026-11-15 04:51 UTC25 files · 3.21 GB

Use it

$ fw get cross-encoder/quora-distilroberta-base
# manifest sha256 cf894212936b… · 3.21 GB · 25 files
$ fw verify ./quora-distilroberta-base cross-encoder/quora-distilroberta-base
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/cross-encoder/quora-distilroberta-base.json --dir ./quora-distilroberta-base $ python3 fw.py verify ./quora-distilroberta-base ./cross-encoder__quora-distilroberta-base.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download cross-encoder/quora-distilroberta-base --revision f62e7a4b20b97195c2868e53ec59126df5eac743 --local-dir ./quora-distilroberta-base

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
59baa6da620d95c9045e86a091d84e00074c42ec40c1cc04d4799914ee4fe6b7
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: quora-distilroberta-baseDate: 2026-11-15Commit: f62e7a4Signed: 2DC28CC7B26A283B ✓
Upstream
cross-encoder/quora-distilroberta-base
Pinned commit
f62e7a4b20b97195c2868e53ec59126df5eac743
Manifest
quora-distilroberta-base.json · .minisig
Manifest sha256
cf894212936b77d54606f6e33f0d193800f1f321a4b71b05d6a2d405e295d09a
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:51 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/cross-encoder/quora-distilroberta-base.json $ curl -O https://freeweights.allternit.com/manifests/cross-encoder/quora-distilroberta-base.json.minisig $ minisign -Vm quora-distilroberta-base.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

distilbert/distilroberta-base · 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/quora-distilroberta-base
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. quora-distilroberta-base.json. Provenance. Takedown history: none.
Source
huggingface.co/cross-encoder/quora-distilroberta-base

Related models

All of alt.freeweights.vision →
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