CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-VL-Embedding-2B
From: Qwen <huggingface.co/Qwen>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-VL-Embedding-2B

Date: 2026-11-14Commit: 9f2f7e7Signed: 2DC28CC7B26A283B ✓

Sentence similarity model with 2.1B parameters. Safetensors weights, 4.27 GB in all. Published by Qwen under Apache-2.0.

2.1B params4.27GBQwen3-VL-Embedding-2Bsafetensorspermissive
FactsParams2.1BSize4.27 GBFormatssafetensorsTasksentence similarityLicenseApache-2.0From sourcepermissive
$ fw get Qwen/Qwen3-VL-Embedding-2B
# manifest sha256 01d00e3d7945… · 4.27 GB · 18 files
$ fw verify ./Qwen3-VL-Embedding-2B Qwen/Qwen3-VL-Embedding-2B
From sourceQwen/Qwen3-VL-Embedding-2BLast check: 2026-11-14 06:35 UTC
OverviewFilesUse itLicenseProvenance

Overview

Size
4.27 GB
Weights
4.26 GB (safetensors)
Parameters
2.1B
Formats
safetensors
Task
sentence similarity
License
Apache-2.0 (permissive)
Files
18, each with a sha256
Publisher
Qwen
Added
2026-11-14
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-VL-2B-Instruct

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 06:35 UTCpassed

Files

18 files · 4.27 GBWeights 4.26 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 18 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
1_Pooling/config.json96 Bde764e01a063fc5f2e96100099bf745695edaaf904107fb3d24fbf4b106f488b
README.md24.2 KB0c01437645b55e91c0145f7f3d9d414d0091cefe53c5f17938949f4c4baad0f2
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja5.52 KBa47e6afb389f86f45be7810f17d2686fd42b2bec7ba6e6958abf85845af258c5
config.json1.57 KB9172f55b0b9cce70b7f67b10c58a408ccf3ec15c587e6efd4d5f41631237fded
config_sentence_transformers.json238 Bab0d95430e4a88750bf613c7bea69cf878818a77c4047150599e1b586a7e8ab0
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model.safetensors4.26 GBc73fa9caeddeb3ff831d46c085a7a5708343248ca777e90f2d486964464509c1
modules.json429 Bfa7d796a215e1b2416773062891923b191fc5a4849bc44e322997433c90f459c
preprocessor_config.json783 Bd75c1f9f474add87cb0188d43c4fbf5c232d2af64f156fcefc5311089049100d
scripts/qwen3_vl_embedding.py13.3 KB8ffa74a1a6bb759610c57865ea416fd4daf9936cb787520e1112a3e1d547f36a
sentence_bert_config.json770 B2c9dac0bf11e4282254502891eb84082debd7a68a775564c75303392f63787f8
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBdef76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a
tokenizer_config.json5.40 KB355f2b4e5bad7b01f11ef6cb68ebc176f61b95c3276092ea225b1bea0e01e95c
video_preprocessor_config.json817 B59c5c9eb52182eb14c06ffb10ca9effd29adce5f238a95de23ca14a38dbd2cb1
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910

Use it

$ fw get Qwen/Qwen3-VL-Embedding-2B
# manifest sha256 01d00e3d7945… · 4.27 GB · 18 files
$ fw verify ./Qwen3-VL-Embedding-2B Qwen/Qwen3-VL-Embedding-2B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/Qwen/Qwen3-VL-Embedding-2B.json --dir ./Qwen3-VL-Embedding-2B $ python3 fw.py verify ./Qwen3-VL-Embedding-2B ./Qwen__Qwen3-VL-Embedding-2B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Qwen/Qwen3-VL-Embedding-2B --revision 9f2f7e710d6d81056aa5c0a4f04764fec6bb7bda --local-dir ./Qwen3-VL-Embedding-2B
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModel, AutoTokenizer tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-VL-Embedding-2B", revision="9f2f7e710d6d81056aa5c0a4f04764fec6bb7bda") model = AutoModel.from_pretrained("Qwen/Qwen3-VL-Embedding-2B", revision="9f2f7e710d6d81056aa5c0a4f04764fec6bb7bda", device_map="auto")
Run in Allternit Desktopcoming in Phase 1
Fine-tune in Freeweights Studiocoming in Phase 3

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Text in
README.md
Text sha256
0c01437645b55e91c0145f7f3d9d414d0091cefe53c5f17938949f4c4baad0f2
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license list. A custom license passes only after a recorded human audit.

Provenance

From: Qwen <huggingface.co/Qwen>Newsgroups: alt.freeweights.qwenSubject: Qwen3-VL-Embedding-2BDate: 2026-11-14Commit: 9f2f7e7Signed: 2DC28CC7B26A283B ✓
Upstream
Qwen/Qwen3-VL-Embedding-2B
Pinned commit
9f2f7e710d6d81056aa5c0a4f04764fec6bb7bda
Manifest
Qwen3-VL-Embedding-2B.json · .minisig
Manifest sha256
01d00e3d79456784086ddd3a870f0969a86f8f7b54192e2a354d75d8fa6ef0f5
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 06:35 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/Qwen/Qwen3-VL-Embedding-2B.json $ curl -O https://freeweights.allternit.com/manifests/Qwen/Qwen3-VL-Embedding-2B.json.minisig $ minisign -Vm Qwen3-VL-Embedding-2B.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

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Qwen/Qwen3-VL-Embedding-2B
Run in Allternit Desktopcoming in Phase 1
Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3-VL-Embedding-2B.json. Provenance. Takedown history: none.
Source
huggingface.co/Qwen/Qwen3-VL-Embedding-2B

Related models

All of alt.freeweights.qwen →
From: unsloth <huggingface.co/unsloth>Subject: Qwen3.8-Flash-Next-GGUF
From: XiaomiMiMo <huggingface.co/XiaomiMiMo>Subject: MiMo-V2.6-Distill-Qwen-9B
From: Qwen <huggingface.co/Qwen>Subject: Qwen-AgentWorld-35B-A3B
From: Qwen <huggingface.co/Qwen>Subject: Qwen-Image-2.1
From: Qwen <huggingface.co/Qwen>Subject: Qwen-Image-2.1-Turbo
From: Qwen <huggingface.co/Qwen>Subject: Qwen3-ASR-1.7B