VIRTUE-2B-SCaR

A Image to Text model by Sony

Sony 146 downloads unknown Image to Text
Frameworkstransformerspytorch
Languagesen
DatasetsTIGER-Lab/MMEB-trainSony/SCaR-Train
PapersarXiv:2510.00523
Tagsqwen2_vlimage-text-to-textEmbeddingbase_model:Qwen/Qwen2-VL-7B-Instructbase_model:finetune:Qwen/Qwen2-VL-7B-Instruct
Downloads
146
License
unknown
Pipeline
Image to Text
Author
Sony

Run VIRTUE-2B-SCaR locally on a Q4KM hard drive

Pre-loaded and ready to run. No download time. No configuration.

Shop Q4KM Drives

Related Image to Text Models

Q
Image to Text
Qwen2.5-VL-3B-Instruct
by Qwen
Qwen2.5‑VL‑3B‑Instruct is the 3‑billion‑parameter instruction‑tuned variant of the Qwen2.5...
21.5Mmpl
Q
Image to Text
Qwen2.5-VL-7B-Instruct
by Qwen
What is this model? Qwen2.5‑VL‑7B‑Instruct is an instruction‑tuned, multimodal large language model...
3.1Mapache-2.0
D
Image to Text
DeepSeek-OCR
by deepseek-ai
DeepSeek‑OCR (model ID deepseek-ai/DeepSeek-OCR ) is a multilingual vision‑language model that...
3.1Mmit
Q
Image to Text
Qwen3-VL-8B-Instruct
by Qwen
Qwen3‑VL‑8B‑Instruct is the latest vision‑language model (VLM) in the Qwen series, built by the...
3.1Mapache-2.0

Pre-loaded AI models. Ready to run.

Skip the downloads. Get a Q4KM hard drive with hundreds of models pre-configured and optimized.

Shop Q4KM Hard Drives