CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.olmo / SAGE-MM-Qwen3-VL-8B-SFT_RL
From: allenai <huggingface.co/allenai>Newsgroups: alt.freeweights.olmoSubject:

SAGE-MM-Qwen3-VL-8B-SFT_RL

Date: 2026-11-15Commit: bd50b52Signed: 2DC28CC7B26A283B ✓

Video text to text model with 8.8B parameters. Safetensors weights, 35.1 GB in all. Published by allenai under Apache-2.0.

8.8B params35.1GBSAGE-MM-Qwen3-VL-8B-SFT_RLsafetensorspermissive
FactsParams8.8BSize35.1 GBFormatssafetensorsTaskvideo text to textLicenseApache-2.0From sourcepermissive
$ fw get allenai/SAGE-MM-Qwen3-VL-8B-SFT_RL
# manifest sha256 cbe6673e0e81… · 35.1 GB · 23 files
$ fw verify ./SAGE-MM-Qwen3-VL-8B-SFT_RL allenai/SAGE-MM-Qwen3-VL-8B-SFT_RL
From sourceHosted (signed)allenai/SAGE-MM-Qwen3-VL-8B-SFT_RLLast check: 2026-11-15 04:14 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-Qwen3-VL-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
35.1 GB
Weights
35.1 GB (safetensors)
Parameters
8.8B
Formats
safetensors
Task
video text to text
License
Apache-2.0 (permissive)
Files
23, 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-Qwen3-VL-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 04:14 UTCpassed

Model card

From the publisher at commit bd50b52. 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

23 files · 35.1 GBWeights 35.1 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 23 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.98 KB62247bb7bcdf7a980e446e92b4a0cd0ea431c88a0fb5da3c116181c43cf5017c
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja5.29 KB3636d0f0bd6bef02654cdffdc447b79cb2cef8ab02cc75267345946291a489e4
config.json1.59 KBcdc184795737e1a21e7cae807f02c404cd0336377472fa0351ccfaa5c921c352
generation_config.json199 Ba0acd9cf47909f86b54951dbf2cfd2af3b0b36178211926760a3a27edb49378d
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
metadata.txt272 B49d4b800532f5ceee158560f528a1f03796b275e9c7facae5e292d72edba3772
model-00001-of-00008.safetensors4.96 GB7e5c9af9b16ed13e3e6903e08de0c64d155207e60f0d10ad5646c0aba874cc64
model-00002-of-00008.safetensors4.83 GB34f1d4d40340f59a87d2ca509e051aa0fedeca53929926d6b88f55b215bc0891
model-00003-of-00008.safetensors4.83 GBd630d91d6b59a66bb071b89e2a5a3c163db3343befe2b148d9a62851f9f1f3f5
model-00004-of-00008.safetensors5.00 GBce406b05d1e09baf7fe242e8847ff2db8550841f5aa36ad0fe74e1daa710d3cc
model-00005-of-00008.safetensors4.83 GB1bf5dd6c89e8352c5be03a6972ca9dfee318d60a34d4bab26f255ebbdeb4434c
model-00006-of-00008.safetensors4.83 GB242ab54825c777d1aa72fdf629498a0a6aef75b6bec8916c86a48df01cdd3c3d
model-00007-of-00008.safetensors3.29 GB661ee031cb2ef6c1756751dbb40ae0c1a20a3f4489aedcd632af11429e2e4cda
model-00008-of-00008.safetensors2.49 GB7d0802916e6890d11cf51561cd17d44cca8e551b8f9d5225aae6095332fb6a8a
model.safetensors.index.json67.8 KB9d988f6fcc4beca61719fbafb679aa48db2859b2a6b9ee132b36151b6f36c5ff
preprocessor_config.json782 B93585062a80db5e8ca038efc7726a3e6411d9db948472d81d63c6303993be8c5
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBf54b55fa0c3aba0c91ce09ea79ae4e62da24e2a1a630f96c4bae34aba25e234a
tokenizer_config.json5.55 KBd3ada4329b435d18a4b600e77611a5018f8b13959973c173b2e668fbb7f64027
video_preprocessor_config.json817 B59c5c9eb52182eb14c06ffb10ca9effd29adce5f238a95de23ca14a38dbd2cb1
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
bd50b5200c pinned now2026-11-15 04:14 UTC23 files · 35.1 GB

Use it

$ fw get allenai/SAGE-MM-Qwen3-VL-8B-SFT_RL
# manifest sha256 cbe6673e0e81… · 35.1 GB · 23 files
$ fw verify ./SAGE-MM-Qwen3-VL-8B-SFT_RL allenai/SAGE-MM-Qwen3-VL-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-Qwen3-VL-8B-SFT_RL.json --dir ./SAGE-MM-Qwen3-VL-8B-SFT_RL $ python3 fw.py verify ./SAGE-MM-Qwen3-VL-8B-SFT_RL ./allenai__SAGE-MM-Qwen3-VL-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-Qwen3-VL-8B-SFT_RL --revision bd50b5200c9e48a70d2251b5858d5ab49876a765 --local-dir ./SAGE-MM-Qwen3-VL-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
62247bb7bcdf7a980e446e92b4a0cd0ea431c88a0fb5da3c116181c43cf5017c
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-Qwen3-VL-8B-SFT_RLDate: 2026-11-15Commit: bd50b52Signed: 2DC28CC7B26A283B ✓
Upstream
allenai/SAGE-MM-Qwen3-VL-8B-SFT_RL
Pinned commit
bd50b5200c9e48a70d2251b5858d5ab49876a765
Manifest
SAGE-MM-Qwen3-VL-8B-SFT_RL.json · .minisig
Manifest sha256
cbe6673e0e813025b0e64dd9e43f6e7786ca43c4f57d613d02de3f733aca0d63
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:14 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/allenai/SAGE-MM-Qwen3-VL-8B-SFT_RL.json $ curl -O https://freeweights.allternit.com/manifests/allenai/SAGE-MM-Qwen3-VL-8B-SFT_RL.json.minisig $ minisign -Vm SAGE-MM-Qwen3-VL-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-Qwen3-VL-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-Qwen3-VL-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-Qwen3-VL-8B-SFT_RL.json. Provenance. Takedown history: none.
Source
huggingface.co/allenai/SAGE-MM-Qwen3-VL-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