{"id":"fd8ab4fa-dd30-48c5-84d2-7377426b1156","slug":"hf-model-andaba-tempura-internvl3-2b-gk10cu-r","name":"TEMPURA-InternVL3-2B","description":"Hugging Face model andaba/TEMPURA-InternVL3-2B. Task: video text to text. Library: transformers. 47 downloads.","capabilities":["transformers","safetensors","internvl","image-text-to-text","video","dense-video-captioning","temporal-grounding","highlight-detection","video-reasoning","video-text-to-text","dataset:andaba/TEMPURA-VER","arxiv:2505.01583","base_model:OpenGVLab/InternVL3-2B-hf","base_model:finetune:OpenGVLab/InternVL3-2B-hf","license:other","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":35,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:12.787Z"}