Expanding Performance Boundaries of Open-Source MLLM
OpenGVLab
community
AI & ML interests
Computer Vision
Organization Card
OpenGVLab
Welcome to OpenGVLab! We are a research group from Shanghai AI Lab focused on Vision-Centric AI research. The GV in our name, OpenGVLab, means general vision, a general understanding of vision, so little effort is needed to adapt to new vision-based tasks.
Models
- InternVL: a pioneering open-source alternative to GPT-4V.
- InternImage: a large-scale vision foundation models with deformable convolutions.
- InternVideo: large-scale video foundation models for multimodal understanding.
- VideoChat: an end-to-end chat assistant for video comprehension.
- All-Seeing-Project: towards panoptic visual recognition and understanding of the open world.
Datasets
- ShareGPT4o: a groundbreaking large-scale resource that we plan to open-source with 200K meticulously annotated images, 10K videos with highly descriptive captions, and 10K audio files with detailed descriptions.
- InternVid: a large-scale video-text dataset for multimodal understanding and generation.
Benchmarks
- MVBench: a comprehensive benchmark for multimodal video understanding.
- CRPE: a benchmark covering all elements of the relation triplets (subject, predicate, object), providing a systematic platform for the evaluation of relation comprehension ability.
- MM-NIAH: a comprehensive benchmark for long multimodal documents comprehension.
- GMAI-MMBench: a comprehensive multimodal evaluation benchmark towards general medical AI.
models
89
OpenGVLab/Mono-InternVL-2B
Image-Text-to-Text
•
Updated
•
567
•
6
OpenGVLab/InternVideo2-Chat-8B
Video-Text-to-Text
•
Updated
•
1.2k
•
16
OpenGVLab/VideoChat2_HD_stage4_Mistral_7B_hf
Updated
•
77
OpenGVLab/InternVL2-8B
Image-Text-to-Text
•
Updated
•
54.7k
•
134
OpenGVLab/InternVL2-4B
Image-Text-to-Text
•
Updated
•
80.3k
•
35
OpenGVLab/InternVL2-Llama3-76B-AWQ
Image-Text-to-Text
•
Updated
•
932
•
23
OpenGVLab/InternVL2-40B-AWQ
Image-Text-to-Text
•
Updated
•
686
•
15
OpenGVLab/InternVL2-26B-AWQ
Image-Text-to-Text
•
Updated
•
424
•
16
OpenGVLab/InternVL2-8B-AWQ
Image-Text-to-Text
•
Updated
•
1.59k
•
10
OpenGVLab/InternVL2-2B-AWQ
Image-Text-to-Text
•
Updated
•
10.6k
•
13
datasets
29
OpenGVLab/InternVL-Domain-Adaptation-Data
Preview
•
Updated
OpenGVLab/OmniCorpus-CC
Updated
•
1
OpenGVLab/MVBench
Viewer
•
Updated
•
4k
•
136k
•
23
OpenGVLab/GMAI-MMBench
Preview
•
Updated
•
12
OpenGVLab/OmniCorpus-YT
Updated
•
1
•
2
OpenGVLab/VideoMAEv2-TAL-Features
Preview
•
Updated
OpenGVLab/InternVL-SA-1B-Caption
Viewer
•
Updated
•
8.63M
•
7
OpenGVLab/InternVL-Chat-V1-2-SFT-Data
Viewer
•
Updated
•
573k
•
105
•
10
OpenGVLab/InternVL-LaionCOCO-OCR
Updated
OpenGVLab/InternVL-WuKong-OCR
Updated
•
1