CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.gpt-oss / gpt-oss-safeguard-120b
From: openai <huggingface.co/openai>Newsgroups: alt.freeweights.gpt-ossSubject:

gpt-oss-safeguard-120b

Date: 2026-11-14Commit: 3c73911Signed: 2DC28CC7B26A283B ✓

Text generation model with 116.8B parameters. Safetensors weights, 65.3 GB in all. Published by openai under Apache-2.0.

116.8B params65.3GBgpt-oss-safeguard-120bsafetensorspermissive
FactsParams116.8BSize65.3 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get openai/gpt-oss-safeguard-120b
# manifest sha256 c31ccfed0bb3… · 65.3 GB · 27 files
$ fw verify ./gpt-oss-safeguard-120b openai/gpt-oss-safeguard-120b
From sourceHosted (signed)openai/gpt-oss-safeguard-120bLast check: 2026-11-14 21:24 UTC
Run at homeGet help

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

Fine-tune of gpt-oss-120b.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
65.3 GB
Weights
65.2 GB (safetensors)
Parameters
116.8B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
27, each with a sha256
Publisher
openai
Added
2026-11-14
Section
alt.freeweights.gpt-oss
Lineage

Original release from the publisher.

Base model: openai/gpt-oss-120b

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 21:24 UTCpassed

Model card

From the publisher at commit 3c73911. Shown as plain text with links; images open at the publisher.

Image: gpt-oss-safeguard-120b

Try gpt-oss-safeguard · Guide · Model card · OpenAI blog

gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are safety reasoning models built-upon gpt-oss. With these models, you can classify text content based on safety policies that you provide and perform a suite of foundational safety tasks. These models are intended for safety use cases. For other applications, we recommend using gpt-oss models.

This model gpt-oss-safeguard-120b fits into a single H100 GPU (117B parameters with 5.1B active parameters). Check out gpt-oss-safeguard-20b for lower latency (21B parameters with 3.6B active parameters).

Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.

Highlights#

  • Trained to reason about safety : Trained and tuned for safety reasoning to accommodate use cases like LLM input-output filtering, online content labeling and offline labeling for Trust and Safety use cases.
  • Bring your own policy: Interprets your written policy, so it generalizes across products and use cases with minimal engineering.
  • Reasoned decisions, not just scores: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in policy decisions. Keep in mind Raw CoT is meant for developers and safety practitioners. It’s not intended for exposure to general users or use cases outside of safety contexts.
  • Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
  • Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.

Inference examples#

You can use gpt-oss-safeguard-120b and gpt-oss-safeguard-20b similar to gpt-oss-120b and gpt-oss-20b as described in our respective cookbooks. We’ve also provided a detailed prompting guide that provides guidelines for how to craft your policy and use it with the models.

Download the model#

To download the model weights from Hugging Face hub using similar instructions to gpt-oss-120b.

Join the ROOST Model Community#

gpt-oss-safeguard is a model partner of the Robust Open Online Safety Tools (ROOST) Model Community. The ROOST Model Community (RMC) is a group of safety practitioners exploring open source AI models to protect online spaces. As an RMC model partner, OpenAI is committed to incorporating user feedback and jointly iterating on future releases in pursuit of open safety. Visit the RMC GitHub repo to learn more about this partnership and how to get involved.

Resources#

Files

27 files · 65.3 GBWeights 65.2 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 27 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
LICENSE11.4 KBcfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30
README.md4.01 KB144ad44df26c573cebefb59586cd9c0e59e30d6e1a546e58986b1c01828cfc1c
USAGE_POLICY236 Ba48000373022ca5114dc538e01085a3885884f41d4ba5c12dcd30d1e2d21dadf
chat_template.jinja16.7 KB589c73db2f7775c5f946b84bd4695fd3be3612e48ebb69a956dc38b7ec70236d
chat_template.json17.5 KBc8f5c2924c29dc0c6fafb1894863d620b2c0b065a8aef860c79f65b911ef95a7
config.json2.09 KB67b357c4accc71d5abbff009de4086754aa1ab040f35929a97f860204ae2b481
generation_config.json165 B97b165839e19bf43309d1e571d1720ebc081dde24e6722cfb644257215ad1e66
model-00000-of-00014.safetensors4.06 GB390d1940d5157d84236e6ba5c79a0097d604a9cebaa6387a2fc8b50ce193272d
model-00001-of-00014.safetensors4.63 GB78b5c58391bff0fe8b426ec60ac1932777184531aac0ba6011626d76261ba940
model-00002-of-00014.safetensors4.12 GBf82e79ca8696a01f264c431edf7d0f0015d85f35956d293d8311d452f0f34eff
model-00003-of-00014.safetensors4.63 GB005a7e66dccd17585d883c680a97e5fb5187d0a380a626f1723c54830d17112d
model-00004-of-00014.safetensors4.12 GBd3927ad7c48743f98ff4780cc15d1979b8b2bcf3fce08fb0bf104a80916908d4
model-00005-of-00014.safetensors4.63 GB326f07d7ce40a9920aed51ec6ac1237cd3ece080f28c86d6ed0796494c612c7d
model-00006-of-00014.safetensors4.12 GB987b29395f80eb82204284d770fee8aef7f4f5072c893e3a6e0185cd9d5adf9d
model-00007-of-00014.safetensors4.63 GB1cecde8fd7f86f2770f60433654aa1d674f1ebbef786200d129f55cac243e0bc
model-00008-of-00014.safetensors4.12 GBbd85f4d6f369e76e159513428da05e08e1818f84f1c11ecfe24653f34c1771b8
model-00009-of-00014.safetensors4.63 GB279813e394c118754a8f896c8ddfaf670d920d9c59553d6b38144790bd03736e
model-00010-of-00014.safetensors4.17 GB7d23bbff2e2e0d0eda531f56b7d9ad995347a4403d36c1f41d592f75cec51fc5
model-00011-of-00014.safetensors4.63 GB26d9774fcb15ce82e226c8747dfa19aaece0c323bb228789d3fced17b6d586ff
model-00012-of-00014.safetensors4.12 GB1f4bcccbd6fa3fabc9f7d89c8c19b48ab078a48010ddc0cbc395a2ba28c1875f
model-00013-of-00014.safetensors4.63 GB0adcb96bba558ca2878ae1db0eba944286e0534d5a8053a7eddab4864d9aca02
model-00014-of-00014.safetensors4.06 GB590d1238be108961ccb99ab37837191758b354d1bdb9d71e7708b1cc8d7742d7
model.safetensors.index.json54.5 KB685abf16107e5a05e97d5e58476289a8a4501e6c9b8d021fe3e5b459945267df
special_tokens_map.json98 Bdd5e191d20c12d2fee1da5bae14ca1db0f5f4215300af691f23cdee97120a293
tokenizer.json27.9 MB0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
tokenizer_config.json4.20 KB9279e942392b742d633c7adbb89ebe002c98399db8926a7af5125c726f404070
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
3c73911826 pinned now manifest updated, same commit2026-11-14 21:24 UTC27 files · 65.3 GB
3c739118262026-11-14 21:24 UTC27 files · 65.3 GB

Use it

$ fw get openai/gpt-oss-safeguard-120b
# manifest sha256 c31ccfed0bb3… · 65.3 GB · 27 files
$ fw verify ./gpt-oss-safeguard-120b openai/gpt-oss-safeguard-120b
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/openai/gpt-oss-safeguard-120b.json --dir ./gpt-oss-safeguard-120b $ python3 fw.py verify ./gpt-oss-safeguard-120b ./openai__gpt-oss-safeguard-120b.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download openai/gpt-oss-safeguard-120b --revision 3c7391182603991a904031244e7822488c67796d --local-dir ./gpt-oss-safeguard-120b
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("openai/gpt-oss-safeguard-120b", revision="3c7391182603991a904031244e7822488c67796d") model = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-safeguard-120b", revision="3c7391182603991a904031244e7822488c67796d", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve openai/gpt-oss-safeguard-120b --revision 3c7391182603991a904031244e7822488c67796d
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
LICENSE
Text sha256
cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30
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: openai <huggingface.co/openai>Newsgroups: alt.freeweights.gpt-ossSubject: gpt-oss-safeguard-120bDate: 2026-11-14Commit: 3c73911Signed: 2DC28CC7B26A283B ✓
Upstream
openai/gpt-oss-safeguard-120b
Pinned commit
3c7391182603991a904031244e7822488c67796d
Manifest
gpt-oss-safeguard-120b.json · .minisig
Manifest sha256
c31ccfed0bb3fcf9254153b10e79ebf382c3734725c9f2f1a6eeea64732e5a58
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:24 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/openai/gpt-oss-safeguard-120b.json $ curl -O https://freeweights.allternit.com/manifests/openai/gpt-oss-safeguard-120b.json.minisig $ minisign -Vm gpt-oss-safeguard-120b.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

openai/gpt-oss-120b · this model is a finetune of it

3 models in the catalog name this one as their parent.

Quantizations
3
Quantizations 3
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download openai/gpt-oss-safeguard-120b
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. gpt-oss-safeguard-120b.json. Provenance. Takedown history: none.
Source
huggingface.co/openai/gpt-oss-safeguard-120b

Variants

3 quantized or adapter builds of gpt-oss-safeguard-120b. Each has its own license check and page.

SubjectSizeParamsLicenseDate
gpt-oss-safeguard-120b-MLX-MXFP4Hosted (signed) From: lmstudio-community in alt.freeweights.gpt-oss62.2 GB116.8BPermissive2026-11-15gpt-oss-safeguard-120b-GGUFHosted (signed) From: unsloth in alt.freeweights.gpt-oss945 GB—Permissive2026-11-15gpt-oss-safeguard-120b-GGUFHosted (signed) From: lmstudio-community in alt.freeweights.gpt-oss63.4 GB—Permissive2026-11-15

Related models

All of alt.freeweights.gpt-oss →
From: unsloth <huggingface.co/unsloth>Subject: gpt-oss-120b
From: mlx-community <huggingface.co/mlx-community>Subject: gpt-oss-120b-4bit
From: unsloth <huggingface.co/unsloth>Subject: gpt-oss-120b-BF16
From: lmstudio-community <huggingface.co/lmstudio-community>Subject: gpt-oss-120b-GGUF
From: unsloth <huggingface.co/unsloth>Subject: gpt-oss-120b-GGUF
From: lmstudio-community <huggingface.co/lmstudio-community>Subject: gpt-oss-120b-MLX-8bit