InterconnectsArtifacts Hub
withVAILVAIL
All models

OpenMMReasoner-RL

byOpenMMReasonerOpenMMReasoner· 19 Nov 2025
General purposeMultimodal

A Qwen2.5 VL fine-tune, trained with GSPO. (Comes with some open RL data too)

Specs
Params7B
LicenseApache-2.0
Tags
modelsmodels/llmsmodels/llms/multi-modalmodels/llms/reasoningartifacts/17
Resources
Hugging Face — OpenMMReasoner/OpenMMReasoner-RLPaper / tech reportAppeared in Artifacts Log #17
Adoption · Interconnects
RAM score
—
Hugging Face Downloads
11
last 30d
2.2K
all time
HF Likes
18

Relative Adoption Metric contextualizes downloads against the model's size bucket.

Related Models

Similar Models

MolmoAct 7B-D
Ai2Ai209 Aug 2025
MiMo-VL-7B-RL-2508
Xiaomi MiMoXiaomi MiMo07 Aug 2025
OVR-7B-RL
KanghengKangheng01 Jul 2025
RoboBrain2.0-7B
BAAIBAAI06 Jun 2025