CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.vision / esm2_t33_650M_UR50D
From: facebook <huggingface.co/facebook>Newsgroups: alt.freeweights.visionSubject:

esm2_t33_650M_UR50D

Date: 2026-11-14Commit: 08e4846Signed: 2DC28CC7B26A283B ✓

Fill mask model with 652M parameters. Safetensors weights, 7.82 GB in all. Published by facebook under MIT.

652M params7.82GBesm2_t33_650M_UR50Dsafetensorspermissive
FactsParams652MSize7.82 GBFormatssafetensorsTaskfill maskLicenseMITFrom sourcepermissive
$ fw get facebook/esm2_t33_650M_UR50D
# manifest sha256 bc8fd08277d2… · 7.82 GB · 9 files
$ fw verify ./esm2_t33_650M_UR50D facebook/esm2_t33_650M_UR50D
From sourceHosted (signed)facebook/esm2_t33_650M_UR50DLast check: 2026-11-14 21:36 UTC
Fine-tune in StudioRun at homeGet help

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

Runs withBentoMLCTranslate2ExLlamaV2LitServeLocalAItinygradTransformersTriton Inference ServerFine-tune withAccelerateDeepSpeedJAXKerasPyTorch Lightningsd-scriptsSimpleTunerConvert withCore ML ToolsExecuTorchOliveONNXOptimum QuantoOptimumsafetensorstorchaoScan withModelScanpicklescan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
7.82 GB
Weights
2.61 GB (safetensors)
Parameters
652M
Formats
safetensors
Task
fill mask
License
MIT (permissive)
Files
9, each with a sha256
Publisher
facebook
Added
2026-11-14
Section
alt.freeweights.vision
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 21:36 UTCpassed

Model card

From the publisher at commit 08e4846. Shown as plain text with links; images open at the publisher.

ESM-2#

ESM-2 is a state-of-the-art protein model trained on a masked language modelling objective. It is suitable for fine-tuning on a wide range of tasks that take protein sequences as input. For detailed information on the model architecture and training data, please refer to the accompanying paper. You may also be interested in some demo notebooks (PyTorch, TensorFlow) which demonstrate how to fine-tune ESM-2 models on your tasks of interest.

Several ESM-2 checkpoints are available in the Hub with varying sizes. Larger sizes generally have somewhat better accuracy, but require much more memory and time to train:

Checkpoint nameNum layersNum parameters
esm2_t48_15B_UR50D4815B
esm2_t36_3B_UR50D363B
esm2_t33_650M_UR50D33650M
esm2_t30_150M_UR50D30150M
esm2_t12_35M_UR50D1235M
esm2_t6_8M_UR50D68M

Files

9 files · 7.82 GBWeights 2.61 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 9 files with their sha256
FileSizesha256
.gitattributes1.44 KB20cb01c2bd9b0ae0863422f9da41b20f10f93e009e657f411a41402f51ccf391
README.md1.71 KB462a2f24724e19c6be0efab926315c294a863c9a9770e2c8b3d859b2d81a07de
config.json724 B539095c22efc52a09d6147074ba4ca119f76a890df5901213b2b55f7d2f96b2b
model.safetensors2.61 GBa08adabb949fa67ad3c14b509d04fd60368b35007b0095e3358f81200c4f4db0
pytorch_model.bin2.61 GBc874668852c7275a159e2c7ceb6069671d7b1ba2c7b52f59600b34ce0f721008
special_tokens_map.json125 B3aedcd4211c0d43aec4e607ff60a63255f3174ead795e997350f09a5f8cd9ee1
tf_model.h52.61 GB3110b0ee07a47362ff90dc4d780b12287e06f2a09f56c8e117c4aed089fc96b8
tokenizer_config.json95 B7e9161ecdb548ec45a41cbc6b24aa4476fdd418461f491c4207baa99419a29ad
vocab.txt93 B0b82cc0a7c7cf9e567b1e5892d793285b9fbae822c964ca48696f7db44598e03
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
08e4846e53 pinned now manifest updated, same commit2026-11-14 21:36 UTC9 files · 7.82 GB
08e4846e532026-11-14 21:36 UTC9 files · 7.82 GB

Use it

$ fw get facebook/esm2_t33_650M_UR50D
# manifest sha256 bc8fd08277d2… · 7.82 GB · 9 files
$ fw verify ./esm2_t33_650M_UR50D facebook/esm2_t33_650M_UR50D
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/facebook/esm2_t33_650M_UR50D.json --dir ./esm2_t33_650M_UR50D $ python3 fw.py verify ./esm2_t33_650M_UR50D ./facebook__esm2_t33_650M_UR50D.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download facebook/esm2_t33_650M_UR50D --revision 08e4846e537177426273712802403f7ba8261b6c --local-dir ./esm2_t33_650M_UR50D
Run at homeFine-tune in Studio

License

Name
MIT License
Id
MIT
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
462a2f24724e19c6be0efab926315c294a863c9a9770e2c8b3d859b2d81a07de
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: facebook <huggingface.co/facebook>Newsgroups: alt.freeweights.visionSubject: esm2_t33_650M_UR50DDate: 2026-11-14Commit: 08e4846Signed: 2DC28CC7B26A283B ✓
Upstream
facebook/esm2_t33_650M_UR50D
Pinned commit
08e4846e537177426273712802403f7ba8261b6c
Manifest
esm2_t33_650M_UR50D.json · .minisig
Manifest sha256
bc8fd08277d283eb8e2c44bcfc8a5bf6d449763ba12abadfbcc5920a508665ca
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:36 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/facebook/esm2_t33_650M_UR50D.json $ curl -O https://freeweights.allternit.com/manifests/facebook/esm2_t33_650M_UR50D.json.minisig $ minisign -Vm esm2_t33_650M_UR50D.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 facebook/esm2_t33_650M_UR50D
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. esm2_t33_650M_UR50D.json. Provenance. Takedown history: none.
Source
huggingface.co/facebook/esm2_t33_650M_UR50D

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