alt.freeweights.olmo / BAR-2x7B-Safety

From:

allenai <huggingface.co/allenai>Newsgroups: alt.freeweights.olmoSubject:

BAR-2x7B-Safety

Date: 2026-11-15Commit: 020eb76Signed: 2DC28CC7B26A283B ✓

Text generation model with 11.6B parameters. Safetensors weights, 23.3 GB in all. Published by allenai under Apache-2.0.

11.6B params

23.3GBBAR-2x7B-Safetysafetensorspermissive

FactsParams11.6BSize23.3 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get allenai/BAR-2x7B-Safety
# manifest sha256 6b460e5e2d2f… · 23.3 GB · 16 files
$ fw verify ./BAR-2x7B-Safety allenai/BAR-2x7B-Safety

From sourceHosted (signed)allenai/BAR-2x7B-SafetyLast check: 2026-11-15 03:56 UTC

Run at home Get help

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

Works with

Run24 Fine-tune29 Convert15 Evaluate13 Scan13 Apps58

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

vLLM exo Text Generation WebUI

SGLang MLC LLM KTransformers LMCache Xinference LMDeploy mistral.rs Mooncake FlashInfer

Show all 24

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad gpu-unlock Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Convert with

mergekit TensorRT Model Optimizer

LLM Compressor Neural Compressor AutoRound AQLM GPTQModel ONNX Core ML Tools ExecuTorch

Show all 15

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Show all 13

picklescan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 23.3 GB
Weights: 23.3 GB (safetensors)
Parameters: 11.6B
Formats: safetensors
Task: text generation
License: Apache-2.0 (permissive)
Files: 16, each with a sha256
Publisher: allenai
Added: 2026-11-15
Section: alt.freeweights.olmo

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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 03:56 UTC	passed

Model card

From the publisher at commit 020eb76. Shown as plain text with links; images open at the publisher.

BAR#

BAR (Branch-Adapt-Route) is a modular post-training approach that extends a fully post-trained language model with new domain capabilities via independently trained Mixture-of-Experts. Rather than retraining a single model across all domains, BAR trains independent domain experts — each through its own mid-training, supervised finetuning (SFT), and reinforcement learning pipeline — and composes them into a unified model via an MoE architecture with lightweight router training.

All BAR models are built on top of Olmo 2 7B.

Models in the BAR suite#

BAR-7B — initial fully post-trained 7B dense model (the starting point)
BAR-2x7B-Base — 2-expert MoE (anchor + base pre-trained model)
BAR-2x7B-Math-SFT — math expert after mid-training and SFT
BAR-2x7B-Math — math expert after mid-training + SFT + RLVR
BAR-2x7B-Code-SFT — code expert after mid-training and SFT
BAR-2x7B-Code — code expert after mid-training + SFT + RLVR
BAR-2x7B-Tool-Use — tool use expert (SFT only)
BAR-2x7B-Safety — safety expert (SFT only)
BAR-5x7B — final 5-expert MoE combining all experts with a trained router

Results#

Model	Overall	Knowledge	Reasoning	Chat	Math	Code	Tool Use	Safety
BAR-7B	31.3	28.5	29.8	48.9	23.6	11.8	25.3	51.3
BAR-2x7B-Math-SFT	36.8	28.8	31.2	40.9	41.9	20.5	21.6	72.7
BAR-2x7B-Math	39.3	29.0	30.8	42.5	55.8	22.1	19.8	75.4
BAR-2x7B-Code-SFT	38.5	28.8	29.1	40.1	25.5	49.3	19.7	77.3
BAR-2x7B-Code	38.8	28.5	29.2	41.0	26.9	50.4	19.8	75.3
BAR-2x7B-Tool-Use	37.2	28.5	28.7	39.3	21.8	16.9	46.4	79.1
BAR-2x7B-Safety	35.6	28.7	28.8	38.1	22.4	15.7	21.1	94.6
BAR-5x7B	49.1	28.4	30.8	38.7	56.2	49.9	45.6	94.0

Scores are unweighted averages across benchmarks within each category. See the paper for per-benchmark results and full evaluation details.

License#

This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with Ai2's Responsible Use Guidelines.

Files

16 files · 23.3 GBWeights 23.3 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 16 files with their sha256

File	Size	sha256
.gitattributes	1.52 KB	11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md	2.37 KB	4f81343f9be924e0a3506f53cebbc8b35094f4f857d0f89c681a4a7e3377c4d7
chat_template.jinja	1.65 KB	1fd2eac6d6f73da1f9e30d9b0511f91a70cc8455ffffe48d20f48e77357f5029
config.json	767 B	ab13a4b4e2023e6c53c2ebd3fecc19b33239878162f707604aefcdcecbc68581
generation_config.json	140 B	98e184d7f8432c9fc3c1993508bacf016f456abcb205b072576148bc2c793330
merges.txt	917 KB	b6fe424e334903f7fb84d3a106d9730455f4744b9fe3c21ee136d97a00e72502
model-00001-of-00005.safetensors	4.97 GB	01cc8b4310a0af0687e37472ee1046d31937c131ba645738e88b79967b1aa068
model-00002-of-00005.safetensors	4.94 GB	e275ef46829267ea85245dfd9c7e7d1e290b433cbb89b57ab4adbb423194a71a
model-00003-of-00005.safetensors	5.00 GB	54b695f4168de7f3940ac8bd0ee4befebc9aad3f17ee87253eddda550c335a5b
model-00004-of-00005.safetensors	4.95 GB	84e1e9e63a7560dbd8e640227a87ab1693ff30c8f6a7d3d3fdf7f8194c6ae61f
model-00005-of-00005.safetensors	3.39 GB	c84878d476f4911fc9c1e767461f75b9d71616d19f926567c74584069912e538
model.safetensors.index.json	41.5 KB	ee3e3e0e51eed99af504e7ffc7e00c9e1df64564d9f2a6ccff305f097f3665ef
special_tokens_map.json	581 B	78afb564e81264029b25f9caf24bda2521d5bdaeff5cd3fdbc01d3da2e8ce2f2
tokenizer.json	7.14 MB	7738a25c46a6043a0e2e605138851baa450269ce9d800af6ca9bf6192e45510c
tokenizer_config.json	4.32 KB	f7a2753a4ff30657e452c8fef02b9a99a3b900ceb4c65a1e3fbea6a3bfab07a6
vocab.json	1.61 MB	d8eb44d0d51f5e39c9b14825ca8bd10a2500f99c438ca81d4462f0263acd3b53

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
020eb765c7 pinned now	2026-11-15 03:56 UTC	16 files · 23.3 GB

Use it

$ fw get allenai/BAR-2x7B-Safety
# manifest sha256 6b460e5e2d2f… · 23.3 GB · 16 files
$ fw verify ./BAR-2x7B-Safety allenai/BAR-2x7B-Safety

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/allenai/BAR-2x7B-Safety.json --dir ./BAR-2x7B-Safety
$ python3 fw.py verify ./BAR-2x7B-Safety ./allenai__BAR-2x7B-Safety.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download allenai/BAR-2x7B-Safety --revision 020eb765c730eb97c707a78e27079349a382d726 --local-dir ./BAR-2x7B-Safety

transformersLoad the weights in Python.

import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("allenai/BAR-2x7B-Safety", revision="020eb765c730eb97c707a78e27079349a382d726")
model = AutoModelForCausalLM.from_pretrained("allenai/BAR-2x7B-Safety", revision="020eb765c730eb97c707a78e27079349a382d726", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve allenai/BAR-2x7B-Safety --revision 020eb765c730eb97c707a78e27079349a382d726

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. 2026-11-15
Text in: README.md
Text sha256: 4f81343f9be924e0a3506f53cebbc8b35094f4f857d0f89c681a4a7e3377c4d7
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:

allenai <huggingface.co/allenai>Newsgroups: alt.freeweights.olmoSubject: BAR-2x7B-SafetyDate: 2026-11-15Commit: 020eb76Signed: 2DC28CC7B26A283B ✓

Upstream: allenai/BAR-2x7B-Safety
Pinned commit: 020eb765c730eb97c707a78e27079349a382d726
Manifest: BAR-2x7B-Safety.json · .minisig
Manifest sha256: 6b460e5e2d2f542495c45a0e2140ac21ba2c54d978731a6c2ecc9e41a38a51ac
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 03:56 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/allenai/BAR-2x7B-Safety.json
$ curl -O https://freeweights.allternit.com/manifests/allenai/BAR-2x7B-Safety.json.minisig
$ minisign -Vm BAR-2x7B-Safety.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 allenai/BAR-2x7B-Safety

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. BAR-2x7B-Safety.json. Provenance. Takedown history: none.

Source

huggingface.co/allenai/BAR-2x7B-Safety

Related models

All of alt.freeweights.olmo →

From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3-7B-Instruct-GGUF

From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3-7B-Think-GGUF

From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3.1-32B-Instruct-GGUF

From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3.1-32B-Think-GGUF

From: bartowski <huggingface.co/bartowski>Subject: allenai_olmOCR-2-7B-1025-GGUF

From: bartowski <huggingface.co/bartowski>Subject: allenai_olmOCR-7B-0225-preview-GGUF

BAR-2x7B-Safety

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

BAR#

Models in the BAR suite#

Results#

License#

Files

Use it

License

Provenance

How to verify

Model tree

Related models