CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.olmo / SAGE-MM-Qwen2.5-VL-7B-SFT
From: allenai <huggingface.co/allenai>Newsgroups: alt.freeweights.olmoSubject:

SAGE-MM-Qwen2.5-VL-7B-SFT

Date: 2026-11-15Commit: 3c141ddSigned: 2DC28CC7B26A283B ✓

Video text to text model with 8.3B parameters. Safetensors weights, 16.6 GB in all. Published by allenai under Apache-2.0.

8.3B params16.6GBSAGE-MM-Qwen2.5-VL-7B-SFTsafetensorspermissive
FactsParams8.3BSize16.6 GBFormatssafetensorsTaskvideo text to textLicenseApache-2.0From sourcepermissive
$ fw get allenai/SAGE-MM-Qwen2.5-VL-7B-SFT
# manifest sha256 ab42217d3125… · 16.6 GB · 19 files
$ fw verify ./SAGE-MM-Qwen2.5-VL-7B-SFT allenai/SAGE-MM-Qwen2.5-VL-7B-SFT
From sourceHosted (signed)allenai/SAGE-MM-Qwen2.5-VL-7B-SFTLast check: 2026-11-15 03:36 UTC
Run at homeGet help

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

Fine-tune of Qwen2.5-VL-7B-Instruct.

Works with

Run8Fine-tune7Convert8Scan2

Runs with

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

TransformersLocalAItinygradTriton Inference ServerBentoMLCTranslate2ExLlamaV2LitServe
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
16.6 GB
Weights
16.6 GB (safetensors)
Parameters
8.3B
Formats
safetensors
Task
video text to text
License
Apache-2.0 (permissive)
Files
19, each with a sha256
Publisher
allenai
Added
2026-11-15
Section
alt.freeweights.olmo
Lineage

Original release from the publisher.

Base model: Qwen/Qwen2.5-VL-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 03:36 UTCpassed

Model card

From the publisher at commit 3c141dd. Shown as plain text with links; images open at the publisher.

Image: SAGE Teaser

System Capabilities#

SAGE-MM operates as the core decision-maker within the SAGE system. It functions in two distinct stages:

  1. Stage-1 (Context VLM): The model analyzes initial sampled frames and metadata to determine if the query can be answered immediately ("single-turn") or if it requires tool usage ("multi-turn").
  2. Stage-2 (Iterative Reasoner): If tools are needed, the model enters a loop where it calls tools, analyzes their output, and updates its context until a final answer is derived.
Supported Tools#

The model is trained to generate JSON-formatted actions to invoke the following tools:

  • web-search: Search the internet for external knowledge (e.g., sports standings, cast lists).
  • transcribe-speech: Perform ASR on specific timestamped segments of the video.
  • ground-event: Locate start/end timestamps for specific visual events.
  • extract-video-parts: Extract high-resolution frames or subclips from specific timestamps.
  • analyze: Perform detailed visual analysis on extracted media.

Usage#

Note: SAGE-MM outputs JSON action strings. It requires a runtime environment (provided in our GitHub repo) to parse these strings, execute the tools, and feed the observation back to the model.

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

19 files · 16.6 GBWeights 16.6 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 19 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.96 KB955015b6627cc494ee0f2264b9d541a2a95367330e97fae2d82668092f10d98c
added_tokens.json605 B58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
chat_template.jinja1.02 KBa0bc6f6fc7a29a80017a433e8f03a1cc1236e838a944a2d034295a60c4f2fddb
config.json3.13 KB57b57677d064b04f7a0d0bacebfcea038c8ee38e2d146af8a833b9dc1b04e770
generation_config.json188 B3c9b9988bac6f1e62ecd36938ec6e7eba93c98fc925c1fc5d499c81bf6b5cd9b
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00004.safetensors4.97 GBb40864924d777c26ab595c2559bef69e0992ffd090d4d77b489d27a5edbe65e3
model-00002-of-00004.safetensors4.99 GBa6563c750ddbbb24349d1ccce89148b74f27b65b5c6e1cf5c8bc4dac24f0abcd
model-00003-of-00004.safetensors4.93 GB3cc00b1db0a63934a27106206c36cb3a482f26bb9981c7372eafbbe81287c3ee
model-00004-of-00004.safetensors1.69 GB428611c5ce6e91ac4f35e9dfa1b9971a11cf9f0bb42fc37cd26e296e4db81574
model.safetensors.index.json57.7 KB4be35310ddc165e46e88de4c3fec8c1210014b0b8717f4544d82cc740814ae0c
preprocessor_config.json829 Bdfc7263fe735989c65c290d394198c4724d5afc58bf15c815d5e2e25b00b51b1
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBba0c439f7be467bf47d12a7e6f9adc6116201056fc60c67f431c679b7c16afc8
tokenizer_config.json4.73 KBe04be4dd17e9f661bc487ba848a37f66a8f1adf2eef412f5d4ecb40cab4d39e7
training_args.bin8.14 KBa7a92754151f2ca6338e517c9392a81419b004d23ac9ef1001e7a475a0eb605e
video_preprocessor_config.json913 B15bb7c2f2bc95fe9cc3749a4b287872b4886a15e9fcf550a4122a46ae26150bd
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
3c141dd432 pinned now2026-11-15 03:36 UTC19 files · 16.6 GB

Use it

$ fw get allenai/SAGE-MM-Qwen2.5-VL-7B-SFT
# manifest sha256 ab42217d3125… · 16.6 GB · 19 files
$ fw verify ./SAGE-MM-Qwen2.5-VL-7B-SFT allenai/SAGE-MM-Qwen2.5-VL-7B-SFT
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/allenai/SAGE-MM-Qwen2.5-VL-7B-SFT.json --dir ./SAGE-MM-Qwen2.5-VL-7B-SFT $ python3 fw.py verify ./SAGE-MM-Qwen2.5-VL-7B-SFT ./allenai__SAGE-MM-Qwen2.5-VL-7B-SFT.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download allenai/SAGE-MM-Qwen2.5-VL-7B-SFT --revision 3c141dd432294f616bf18538d593d3794a4e29ec --local-dir ./SAGE-MM-Qwen2.5-VL-7B-SFT
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
955015b6627cc494ee0f2264b9d541a2a95367330e97fae2d82668092f10d98c
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: SAGE-MM-Qwen2.5-VL-7B-SFTDate: 2026-11-15Commit: 3c141ddSigned: 2DC28CC7B26A283B ✓
Upstream
allenai/SAGE-MM-Qwen2.5-VL-7B-SFT
Pinned commit
3c141dd432294f616bf18538d593d3794a4e29ec
Manifest
SAGE-MM-Qwen2.5-VL-7B-SFT.json · .minisig
Manifest sha256
ab42217d3125fc3b2b047df1ff3f4afe2ef5550953563612cd56c7980a560fcd
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:36 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/allenai/SAGE-MM-Qwen2.5-VL-7B-SFT.json $ curl -O https://freeweights.allternit.com/manifests/allenai/SAGE-MM-Qwen2.5-VL-7B-SFT.json.minisig $ minisign -Vm SAGE-MM-Qwen2.5-VL-7B-SFT.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-VL-7B-Instruct · this model is a finetune of it

1 model in the catalog name this one as their parent.

Fine-tunes
1
Fine-tunes 1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download allenai/SAGE-MM-Qwen2.5-VL-7B-SFT
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. SAGE-MM-Qwen2.5-VL-7B-SFT.json. Provenance. Takedown history: none.
Source
huggingface.co/allenai/SAGE-MM-Qwen2.5-VL-7B-SFT

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