9Kdl/month
13likes
Identifier
Model ID
TianheWu/VisualQuality-R1-7BTags
safetensorsqwen2_5_vlIQAReasoningVLMPytorchR1GRPORL2Rreinforcement-learningenarxiv:2505.14460base_model:Qwen/Qwen2.5-VL-7B-Instructbase_model:finetune:Qwen/Qwen2.5-VL-7B-Instructlicense:mitregion:us
Use VisualQuality-R1-7B on Mixpeek
Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval in Mixpeek Studio.
Open StudioHow It Runs on Mixpeek
On Mixpeek, VisualQuality-R1-7B runs as a managed extractor inside a processing pipeline. Point a bucket of reinforcement learning data at it, and Mixpeek handles GPU provisioning, batching, retries, and writing the outputs into a vector store you can query.
Extractor outputs land in the Mixpeek Vector Store (MVS), where you can combine them with retrieval, reranking, and filter stages to build end-to-end search and agent-perception pipelines, no model-serving infrastructure to maintain.
Specification
OrganizationTianheWu
TaskReinforcement Learning
Licensemit
Downloads/mo9K
Likes13
View on HuggingFace
See model card, files, and community discussion
Related Reinforcement Learning Models
HumanCompatibleAI/ppo-seals-CartPole-v0
45K
HumanCompatibleAI/ppo-Pendulum-v1
19K
mradermacher/AReaL-SEA-235B-A22B-i1-GGUF
15K
mradermacher/Aryabhata-2.0-i1-GGUF
5K
mradermacher/SpatialThinker-30B-i1-GGUF
4K
mradermacher/GoLongRL-4B-i1-GGUF
3K
mradermacher/TinyResearcher-i1-GGUF
3K
mradermacher/Vero-Qwen35-9B-Base-i1-GGUF
3K