CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.olmo / SAGE-MM-Molmo2-8B-SFT_RL
From: allenai <huggingface.co/allenai>Newsgroups: alt.freeweights.olmoSubject:

SAGE-MM-Molmo2-8B-SFT_RL

Date: 2026-11-15Commit: 55cc705Signed: 2DC28CC7B26A283B ✓

Video text to text model with 8.7B parameters. Safetensors weights, 34.7 GB in all. Published by allenai under Apache-2.0.

8.7B params34.7GBSAGE-MM-Molmo2-8B-SFT_RLsafetensorspermissive
FactsParams8.7BSize34.7 GBFormatssafetensorsTaskvideo text to textLicenseApache-2.0From sourcepermissive
$ fw get allenai/SAGE-MM-Molmo2-8B-SFT_RL
# manifest sha256 38ecd285617a… · 34.7 GB · 35 files
$ fw verify ./SAGE-MM-Molmo2-8B-SFT_RL allenai/SAGE-MM-Molmo2-8B-SFT_RL
From sourceHosted (signed)allenai/SAGE-MM-Molmo2-8B-SFT_RLLast check: 2026-11-15 03:39 UTC
Run at homeGet help

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

Fine-tune of SAGE-MM-Molmo2-8B-SFT.

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
34.7 GB
Weights
34.6 GB (safetensors)
Parameters
8.7B
Formats
safetensors
Task
video text to text
License
Apache-2.0 (permissive)
Files
35, each with a sha256
Publisher
allenai
Added
2026-11-15
Section
alt.freeweights.olmo
Lineage

Original release from the publisher.

Base model: allenai/SAGE-MM-Molmo2-8B-SFT

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 03:39 UTCpassed

Model card

From the publisher at commit 55cc705. 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

35 files · 34.7 GBWeights 34.6 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 35 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.98 KB5f0e6ec0fbcec63b4e9f6c8724b343a4fcd193c0dc3dee5dfb2fc834e3ce9c2d
_fsdp_api.py3.35 KB649484198fd0dba028f25a9f732b59bd7570aaf24082c8d70f056dea3caf89dc
_fsdp_collectives.py26.8 KB3bf079219682d1a9439b81754af65e87f69157ec69f20f065e5565519f7093d9
_fsdp_common.py5.68 KBd9972d8736a93e1e57aca6c9bb247fbfd5ac2b76663984c5de4f2d5bf2217dcb
_fsdp_init.py9.14 KB95cd101f9d5c1da7db1965fc2ecd2b344878e58a4d81299fdad1a1223e0a61aa
_fsdp_param.py41.5 KB12e459491589b623158627846f837175eae353e685f691875b5eb6b7884896e1
_fsdp_param_group.py35.5 KB2798a87b2631091df738afaff6dfcead38ce0cc421585b4331ecaaefb4e784f5
_fsdp_state.py17.8 KB46c55a0b88c364534d8032a14a139a0017a00ddfed1c6b5ffe43cd6a16b3474b
_fully_shard.py30.1 KB901220efd8b6ea015eebd468a689a8edcf5023cfcc3694159d892950261d8e15
added_tokens.json9.92 KB8bc892fbf3933cf0c00794b0f0fa638ca22429db58d427f71ea953accabbf1e7
chat_template.jinja3.17 KBec66862fda57dc1aef90a21b2a0f64c18a280e2483206449bd251a73b8993101
config.json2.56 KBba19c287014d82e470687611b5d44547a9b959b3cfe6da2b4f182736df7f9189
config.py13.5 KBcf7939f9d26cddcf2667460e698fad75f867728428f56c823f31710002dea5fa
generation_config.json139 B8986f817d56dfa289f06d60363c87dc4cd582c302483ba933fe3f17e8bcef588
image_processing.py22.5 KB59080b8e1291deae5d17774d6bb02941875c022ccc0c53e81a3d2551314e75aa
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
metadata.txt259 B711eb6a0eb52579076ede63e1a2cbf25174200d3924c6159f62d64c71a049323
model-00001-of-00008.safetensors4.97 GBa5ff672b561c86469c95a862b9f938f3fcb7354dba9262b65ecf1da05cfc10d5
model-00002-of-00008.safetensors4.63 GBdbc95fe13befa71230353397653d769c09e8bcf64af69973f2cec39b06759325
model-00003-of-00008.safetensors4.63 GB25de3917dece912e071323d3ea12290640baaf442a7df19d906e300f2301484c
model-00004-of-00008.safetensors4.63 GB7a7ec48808283a00a7f18a0aa6fa0eb2559c25f6ea8b4990097af7b1284834a9
model-00005-of-00008.safetensors4.63 GB2ed09b952603d0d6a00aacd769a939f89bff2a5fb1aad6ec80c0cc35973dfa3a
model-00006-of-00008.safetensors4.63 GBd65ef23b6d4adec60145ff8eb415897dcc4a70af0b2ca12028e191fb11055a69
model-00007-of-00008.safetensors4.03 GBa1b7f056b884582e129aaee88ed96f98812f3470c9d312f896be2cf3fb334889
model-00008-of-00008.safetensors2.49 GBc3c1e9210649e365195cb01c95f761235dc19d8ae89469c3ff1cc30e2ee822a5
model.safetensors.index.json75.8 KB09434f42071cd60462fab36d8e455c6d8944cd522c383dd2b5923f6096cc3cda
processing.py47.2 KB940160e7b9b689f0544f600606d907ac46f6db2abe5047af836ba75661f587c0
processor_config.json229 Bac1c38238a0e1da8e940e183234d742fde0b5130f10a27f24294c68297331556
special_tokens_map.json8.02 KB061a078dd1ff8eeb3a8a3d481cff3372065232f34929c6c6ac0e4211ce9d82a1
tokenizer.json11.5 MB5f536b0de2a243509f3a4df21b448c2b4d6e3c6e3da7f529c8cb8268b2eb0efc
tokenizer_config.json64.5 KB8dce8e7665eabf2e5f4243b5a27a72c1813b26e48833d5add3ae8a66bce63147
video_preprocessor_config.json897 B1cb281ef8d5cdb6d14ca438cc2bb5a504a418974598c3fd67013063dc968c8d5
video_processing.py12.9 KB8813c88d05c744976a02918d8ceb2f7b1a424491f06661b8b8e66ee9184a6995
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
55cc7057c8 pinned now2026-11-15 03:39 UTC35 files · 34.7 GB

Use it

$ fw get allenai/SAGE-MM-Molmo2-8B-SFT_RL
# manifest sha256 38ecd285617a… · 34.7 GB · 35 files
$ fw verify ./SAGE-MM-Molmo2-8B-SFT_RL allenai/SAGE-MM-Molmo2-8B-SFT_RL
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-Molmo2-8B-SFT_RL.json --dir ./SAGE-MM-Molmo2-8B-SFT_RL $ python3 fw.py verify ./SAGE-MM-Molmo2-8B-SFT_RL ./allenai__SAGE-MM-Molmo2-8B-SFT_RL.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download allenai/SAGE-MM-Molmo2-8B-SFT_RL --revision 55cc7057c8f7c8560476b5b36f6236bfefbe8d92 --local-dir ./SAGE-MM-Molmo2-8B-SFT_RL
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
5f0e6ec0fbcec63b4e9f6c8724b343a4fcd193c0dc3dee5dfb2fc834e3ce9c2d
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-Molmo2-8B-SFT_RLDate: 2026-11-15Commit: 55cc705Signed: 2DC28CC7B26A283B ✓
Upstream
allenai/SAGE-MM-Molmo2-8B-SFT_RL
Pinned commit
55cc7057c8f7c8560476b5b36f6236bfefbe8d92
Manifest
SAGE-MM-Molmo2-8B-SFT_RL.json · .minisig
Manifest sha256
38ecd285617a344f49140ae21afcda2d61d97d862321dd09118781ba4ec6772a
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:39 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/allenai/SAGE-MM-Molmo2-8B-SFT_RL.json $ curl -O https://freeweights.allternit.com/manifests/allenai/SAGE-MM-Molmo2-8B-SFT_RL.json.minisig $ minisign -Vm SAGE-MM-Molmo2-8B-SFT_RL.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

allenai/SAGE-MM-Molmo2-8B-SFT · this model is a finetune of it

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

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download allenai/SAGE-MM-Molmo2-8B-SFT_RL
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-Molmo2-8B-SFT_RL.json. Provenance. Takedown history: none.
Source
huggingface.co/allenai/SAGE-MM-Molmo2-8B-SFT_RL

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