alt.freeweights.gemma / embeddinggemma-2
From: google <huggingface.co/google>Newsgroups: alt.freeweights.gemmaSubject:

embeddinggemma-2

Date: 2026-11-14Commit: f9972acSigned: 2DC28CC7B26A283B ✓

Feature extraction model with 744M parameters. Safetensors weights, 1.53 GB in all. Published by google under Apache-2.0.

744M params1.53GBembeddinggemma-2safetensorspermissive
FactsParams744MSize1.53 GBFormatssafetensorsTaskfeature extractionLicenseApache-2.0From sourcepermissive
$ fw get google/embeddinggemma-2
# manifest sha256 3a5a41d43d43… · 1.53 GB · 15 files
$ fw verify ./embeddinggemma-2 google/embeddinggemma-2
From sourcegoogle/embeddinggemma-2Last check: 2026-11-14 06:23 UTC

Overview

Size
1.53 GB
Weights
1.49 GB (safetensors)
Parameters
744M
Formats
safetensors
Task
feature extraction
License
Apache-2.0 (permissive)
Files
15, each with a sha256
Publisher
google
Added
2026-11-14
Section
alt.freeweights.gemma
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 06:23 UTCpassed

Files

15 files · 1.53 GBWeights 1.49 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 15 files with their sha256
FileSizesha256
.gitattributes1.30 KBbcdccfaa66bc1240c7192dbd374cfb39b695bb1d8ff6b7ce0113aa5e9ac21a44
1_Pooling/config.json90 B8759bdf7c77efc7df7723f64856a593c8943b71ee38baf2a88771fbaf78438f9
2_Normalize/config.json97 Bcdb09dfca347a56aa2d691744e38d5ad3c7cbc2834e7181272b9a15328b82524
README.md22.2 KB2c058c304c68221f1de80979594036eff3972b2bce686bb7b0f43621a6b0b011
chat_template.jinja1.02 KB4b852efc0b9960283e735363331e6f325b33bc74bdbaa076f595bc4e9b94d85e
config.json4.46 KBb8f1e9931b57fbc054acdb445c41765d55b0074c58d145fa82839941ad1b5bb3
config_sentence_transformers.json1.56 KB031e56a498d33c349ab489a21885bcfe25b4fcba841149dc99e1e90d4a7c28f5
model.safetensors1.49 GB197a32965d4b1105faf060417baa899e193fb73cd401f42ec9295234d5553d79
modules.json413 B3d02572a0455b832de67fb8e63a54981bc7e8b46e337c95e917bd8122a533bfd
preprocessor_config.json511 Bea2ae257e901064abdd98dceb19f2b0da06af600bed15e0f99f5c85c37ee9d78
processor_config.json1.79 KB168f6a08522f3ce5dea596d94d003af2fd691742d4f41fe1f9d8cce76bfbf69c
sentence_bert_config.json747 Bb1bcd9f2dce3ae863b359e87d0710b5dbc3314a59ecb4e2f97c7778fc8e4b228
tokenizer.json32.2 MB4d777ef5bdc1aa36227abdfb77c3e49e7b9c892d16e1b6bda41c393504828be4
tokenizer.model4.69 MBe594c8a90eb08d8bda498ff4747977dc827ae0c3c56b5c0d41a605a22d02ef03
tokenizer_config.json1.60 KB17bd5d6e9364ca49a534e1502076593317c298d4a663623091ed45388f004874

Use it

$ fw get google/embeddinggemma-2
# manifest sha256 3a5a41d43d43… · 1.53 GB · 15 files
$ fw verify ./embeddinggemma-2 google/embeddinggemma-2
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/google/embeddinggemma-2.json --dir ./embeddinggemma-2 $ python3 fw.py verify ./embeddinggemma-2 ./google__embeddinggemma-2.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download google/embeddinggemma-2 --revision f9972ac22e696a105c482202646979e33e4b5a1e --local-dir ./embeddinggemma-2
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModel, AutoTokenizer tok = AutoTokenizer.from_pretrained("google/embeddinggemma-2", revision="f9972ac22e696a105c482202646979e33e4b5a1e") model = AutoModel.from_pretrained("google/embeddinggemma-2", revision="f9972ac22e696a105c482202646979e33e4b5a1e", 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
2c058c304c68221f1de80979594036eff3972b2bce686bb7b0f43621a6b0b011
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: google <huggingface.co/google>Newsgroups: alt.freeweights.gemmaSubject: embeddinggemma-2Date: 2026-11-14Commit: f9972acSigned: 2DC28CC7B26A283B ✓
Upstream
google/embeddinggemma-2
Pinned commit
f9972ac22e696a105c482202646979e33e4b5a1e
Manifest
embeddinggemma-2.json · .minisig
Manifest sha256
3a5a41d43d43590486a4d4120bae1dd4a1658dcd064ebd11152550ae9fd38b7e
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 06:23 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/google/embeddinggemma-2.json $ curl -O https://freeweights.allternit.com/manifests/google/embeddinggemma-2.json.minisig $ minisign -Vm embeddinggemma-2.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 google/embeddinggemma-2
Run in Allternit Desktopcoming in Phase 1
Signed manifest
minisign, key 2DC28CC7B26A283B. embeddinggemma-2.json. Provenance. Takedown history: none.
From: google <huggingface.co/google>Subject: gemma-4-12B-it
From: google <huggingface.co/google>Subject: gemma-4-26B-A4B-it
From: google <huggingface.co/google>Subject: gemma-4-31B-it
From: google <huggingface.co/google>Subject: gemma-4-E2B-it
From: google <huggingface.co/google>Subject: gemma-4-E4B-it