CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.embed / stsb-TinyBERT-L4
From: cross-encoder <huggingface.co/cross-encoder>Newsgroups: alt.freeweights.embedSubject:

stsb-TinyBERT-L4

Date: 2026-11-14Commit: 1f47848Signed: 2DC28CC7B26A283B ✓

Text ranking model with 14M parameters. Onnx and openvino and safetensors weights, 563 MB in all. Published by cross-encoder under Apache-2.0.

14M params563MBstsb-TinyBERT-L4onnx openvino safetensorspermissive
FactsParams14MSize563 MBFormatsonnx, openvino, safetensorsTasktext rankingLicenseApache-2.0From sourcepermissive
$ fw get cross-encoder/stsb-TinyBERT-L4
# manifest sha256 ecb63da398f6… · 563 MB · 24 files
$ fw verify ./stsb-TinyBERT-L4 cross-encoder/stsb-TinyBERT-L4
From sourceHosted (signed)cross-encoder/stsb-TinyBERT-L4Last check: 2026-11-14 21:08 UTC
Run at homeGet help

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

Works with

Run11Fine-tune8Convert8Evaluate1Scan2Apps16

Evaluate with

MTEB
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
563 MB
Weights
57.4 MB (safetensors)
Parameters
14M
Formats
onnx, openvino, safetensors
Task
text ranking
License
Apache-2.0 (permissive)
Files
24, each with a sha256
Publisher
cross-encoder
Added
2026-11-14
Section
alt.freeweights.embed
Lineage

Original release from the publisher.

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.co2026-11-14 21:08 UTCpassed

Model card

From the publisher at commit 1f47848. 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-TinyBERT-L4')
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

24 files · 563 MBWeights 57.4 MB (safetensors). Sizes and sha256 from the signed manifest.
Show all 24 files with their sha256
FileSizesha256
.gitattributes445 B98c91dabef4df27b2fc7c8454d220aba47476f73593cbd034d961fe4927304c1
CECorrelationEvaluator_sts-dev_results.csv311 B9e1c4c54d912094707474c3f589addb202777a6c767c75bde17d60175469c9ca
README.md1.10 KBf82d49e59999baa3c38909ac967c641cb2c06f3a2b01748f9aaa65397756d67c
config.json647 B190ccd33b3a8c168cbda611a5d38ed47c9f21e5cfe88444fa2d8fd286994b3f6
flax_model.msgpack57.4 MBec046a6abe4d2302f8ac8a06ad8d90957d1e6e937411753d7a865860bc696c9c
model.safetensors57.4 MB4fa70fae4092a08c5d1dcffc720318e5cbd4f8208b2213ebdb2d9525f89aabf5
onnx/model.onnx57.5 MB8a083b28b32cca196730541bb3d0874c73cb11ec6e8a192273d088e1fbac2388
onnx/model_O1.onnx57.5 MBa1300e70a3510de85dbcdfeda810b99379f67f173c3c813bbbfe0b74fa0b62a6
onnx/model_O2.onnx57.4 MB9d73135beeca73f916a4db31da46e3d551b496480b2173ac71819d7f2e1491b0
onnx/model_O3.onnx57.4 MB4e99a59ad7b0dfcd597deba6beb74c97195ab3b0e45b6faf59c972ca3e95f931
onnx/model_O4.onnx28.8 MB4b6ce4d7445228291d6de39e27c824b9571141694624c444ed8b6f196d38d264
onnx/model_qint8_arm64.onnx14.7 MB75eb42eceab4bded3be613c125803863f37312dd1740180b0b7db4c684454764
onnx/model_qint8_avx512.onnx14.7 MB75eb42eceab4bded3be613c125803863f37312dd1740180b0b7db4c684454764
onnx/model_qint8_avx512_vnni.onnx14.7 MB75eb42eceab4bded3be613c125803863f37312dd1740180b0b7db4c684454764
onnx/model_quint8_avx2.onnx14.7 MBea95077b3644ca53770b83af890a7758311270809c2832c8b47146454847a506
openvino/openvino_model.bin57.4 MB1d1ce9851caab609548ab56661d46b1ed873bbf1abf2ebb07b17438e98ebd344
openvino/openvino_model.xml147 KB54ddd6d49160ce9313b60b51efd4e5eb7d901faa98a5ee03555e195a656452b5
openvino/openvino_model_qint8_quantized.bin14.6 MB8d825a0ca34c76d4e8617c5f5d9dc169baa11074c46e9a7ee43acf38d9aadfa0
openvino/openvino_model_qint8_quantized.xml263 KB9ece4be8686c84de7753d9ef4c841067276c56a138bf8b142d4bce2886ea8191
pytorch_model.bin57.4 MBc81276416deab713ab841b7d4afa2484270d5d23d735d1baa27a7bc1501080e2
special_tokens_map.json132 B3c3507f36dff57bce437223db3b3081d1e2b52ec3e56ee55438193ecb2c94dd6
tokenizer.json711 KBd241a60d5e8f04cc1b2b3e9ef7a4921b27bf526d9f6050ab90f9267a1f9e5c66
tokenizer_config.json1.33 KBa5c2e5a7b1a29a0702cd28c08a399b5ecc110c263009d17f7e3b415f25905fd8
vocab.txt232 KB07eced375cec144d27c900241f3e339478dec958f92fddbc551f295c992038a3
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
1f47848214 pinned now manifest updated, same commit2026-11-14 21:08 UTC24 files · 563 MB
1f478482142026-11-14 21:08 UTC24 files · 563 MB

Use it

$ fw get cross-encoder/stsb-TinyBERT-L4
# manifest sha256 ecb63da398f6… · 563 MB · 24 files
$ fw verify ./stsb-TinyBERT-L4 cross-encoder/stsb-TinyBERT-L4
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-TinyBERT-L4.json --dir ./stsb-TinyBERT-L4 $ python3 fw.py verify ./stsb-TinyBERT-L4 ./cross-encoder__stsb-TinyBERT-L4.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download cross-encoder/stsb-TinyBERT-L4 --revision 1f478482145797a0cac02d6b9ab3c65c9d25fb1e --local-dir ./stsb-TinyBERT-L4
Run at home

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. 2026-11-14
Text in
README.md
Text sha256
f82d49e59999baa3c38909ac967c641cb2c06f3a2b01748f9aaa65397756d67c
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.embedSubject: stsb-TinyBERT-L4Date: 2026-11-14Commit: 1f47848Signed: 2DC28CC7B26A283B ✓
Upstream
cross-encoder/stsb-TinyBERT-L4
Pinned commit
1f478482145797a0cac02d6b9ab3c65c9d25fb1e
Manifest
stsb-TinyBERT-L4.json · .minisig
Manifest sha256
ecb63da398f623768dcca86ae1e9c2d11a7b3ffc65d486c102f53f0bf9b4a9a0
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:08 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/cross-encoder/stsb-TinyBERT-L4.json $ curl -O https://freeweights.allternit.com/manifests/cross-encoder/stsb-TinyBERT-L4.json.minisig $ minisign -Vm stsb-TinyBERT-L4.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

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download cross-encoder/stsb-TinyBERT-L4
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. stsb-TinyBERT-L4.json. Provenance. Takedown history: none.
Source
huggingface.co/cross-encoder/stsb-TinyBERT-L4

Related models

All of alt.freeweights.embed →
From: sentence-transformers <huggingface.co/sentence-transformers>Subject: all-MiniLM-L6-v1
From: unsloth <huggingface.co/unsloth>Subject: all-MiniLM-L6-v2
From: mlx-community <huggingface.co/mlx-community>Subject: all-MiniLM-L6-v2-4bit
From: sentence-transformers <huggingface.co/sentence-transformers>Subject: all-mpnet-base-v1
From: sentence-transformers <huggingface.co/sentence-transformers>Subject: allenai-specter
From: sentence-transformers <huggingface.co/sentence-transformers>Subject: bert-base-nli-max-tokens