CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / HARC-Qwen2.5-7B-Instruct
From: microsoft <huggingface.co/microsoft>Newsgroups: alt.freeweights.qwenSubject:

HARC-Qwen2.5-7B-Instruct

Date: 2026-11-15Commit: f650ffaSigned: 2DC28CC7B26A283B ✓

Text generation model with 7.6B parameters. Safetensors weights, 15.2 GB in all. Published by microsoft under Apache-2.0.

7.6B params15.2GBHARC-Qwen2.5-7B-Instructsafetensorspermissive
FactsParams7.6BSize15.2 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get microsoft/HARC-Qwen2.5-7B-Instruct
# manifest sha256 5a856ad2ce5b… · 15.2 GB · 16 files
$ fw verify ./HARC-Qwen2.5-7B-Instruct microsoft/HARC-Qwen2.5-7B-Instruct
From sourceHosted (signed)microsoft/HARC-Qwen2.5-7B-InstructLast check: 2026-11-15 03:28 UTC
Run at homeGet help

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

Merge of Qwen2.5-7B-Instruct.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
15.2 GB
Weights
15.2 GB (safetensors)
Parameters
7.6B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
16, each with a sha256
Publisher
microsoft
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen2.5-7B-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.co2026-11-15 03:28 UTCpassed

Model card

From the publisher at commit f650ffa. Shown as plain text with links; images open at the publisher.

HARC — Qwen2.5-7B-Instruct#

HARC safety-alignment LoRA merged into Qwen/Qwen2.5-7B-Instruct (full standalone model). Part of the HARC release; see paper arXiv:2607.00572.

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("microsoft/HARC-Qwen2.5-7B-Instruct", torch_dtype="bfloat16", device_map="auto")
tok = AutoTokenizer.from_pretrained("microsoft/HARC-Qwen2.5-7B-Instruct")

Files

16 files · 15.2 GBWeights 15.2 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 16 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md667 B85c83ec8d6c132aeb62d499584168a927b2bf2979980da4af191e526462aaff3
added_tokens.json605 B58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
chat_template.jinja2.51 KBcd8e9439f0570856fd70470bf8889ebd8b5d1107207f67a5efb46e342330527f
config.json687 B14428f164ce20feb1ede5e3ecdcb302edf7e7763c44fa3977d319870af6b0710
generation_config.json243 B56f7a098fe2da207676326ab02a0564a544aefd0ba309208f033cc3b72c501a0
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00004.safetensors4.88 GB98311a6c46a71bcff17e356df7cb57d710e8fedf012e2a4f097d4297563873df
model-00002-of-00004.safetensors4.93 GB3bd8ec1ecc9319fed77b39aa48a668910df2b010a553b41e5a98fdaf26979402
model-00003-of-00004.safetensors4.33 GB19a13c250649b6390578a29b4765e0133a297860062aae30e933cf7e80eb3d7e
model-00004-of-00004.safetensors1.09 GB06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2
model.safetensors.index.json27.8 KB998a078123ffc97763690de7f2a677eb89168af5eaf8a5e12e6bc24d18e25bdb
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBe1bb43ac6226b35aa5fb20bf7f7eeb9c8c63289288dc1ce1ea4c7c69d8079a1d
tokenizer_config.json4.79 KBade02f0209384e79081bff48fc4803920f61fe909c7beb102c9b086a6dacb51e
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
f650ffae02 pinned now2026-11-15 03:28 UTC16 files · 15.2 GB

Use it

$ fw get microsoft/HARC-Qwen2.5-7B-Instruct
# manifest sha256 5a856ad2ce5b… · 15.2 GB · 16 files
$ fw verify ./HARC-Qwen2.5-7B-Instruct microsoft/HARC-Qwen2.5-7B-Instruct
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/microsoft/HARC-Qwen2.5-7B-Instruct.json --dir ./HARC-Qwen2.5-7B-Instruct $ python3 fw.py verify ./HARC-Qwen2.5-7B-Instruct ./microsoft__HARC-Qwen2.5-7B-Instruct.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download microsoft/HARC-Qwen2.5-7B-Instruct --revision f650ffae020ad9cfd957d5a341750226843ae89e --local-dir ./HARC-Qwen2.5-7B-Instruct
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("microsoft/HARC-Qwen2.5-7B-Instruct", revision="f650ffae020ad9cfd957d5a341750226843ae89e") model = AutoModelForCausalLM.from_pretrained("microsoft/HARC-Qwen2.5-7B-Instruct", revision="f650ffae020ad9cfd957d5a341750226843ae89e", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve microsoft/HARC-Qwen2.5-7B-Instruct --revision f650ffae020ad9cfd957d5a341750226843ae89e
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
85c83ec8d6c132aeb62d499584168a927b2bf2979980da4af191e526462aaff3
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: microsoft <huggingface.co/microsoft>Newsgroups: alt.freeweights.qwenSubject: HARC-Qwen2.5-7B-InstructDate: 2026-11-15Commit: f650ffaSigned: 2DC28CC7B26A283B ✓
Upstream
microsoft/HARC-Qwen2.5-7B-Instruct
Pinned commit
f650ffae020ad9cfd957d5a341750226843ae89e
Manifest
HARC-Qwen2.5-7B-Instruct.json · .minisig
Manifest sha256
5a856ad2ce5b3b350eb41a4ec79844167f9bac22d71f59152dbb30af0ca7efcc
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:28 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/microsoft/HARC-Qwen2.5-7B-Instruct.json $ curl -O https://freeweights.allternit.com/manifests/microsoft/HARC-Qwen2.5-7B-Instruct.json.minisig $ minisign -Vm HARC-Qwen2.5-7B-Instruct.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

Qwen/Qwen2.5-7B-Instruct · this model is a merge of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download microsoft/HARC-Qwen2.5-7B-Instruct
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. HARC-Qwen2.5-7B-Instruct.json. Provenance. Takedown history: none.
Source
huggingface.co/microsoft/HARC-Qwen2.5-7B-Instruct

Related models

All of alt.freeweights.qwen →
From: BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen
From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1
From: BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923
From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct
From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA
From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF