MiniCPM-V: A GPT-4V Level MLLM on Your Phone
Paper
•
2408.01800
•
Published
•
90
MiniCPM-o & MiniCPM-V
Multimodal models with leading performance.
-
-
openbmb/MiniCPM-o-4_5
Any-to-Any • 9B • Updated • 40.4k • 998 -
openbmb/MiniCPM-o-4_5-gguf
Any-to-Any • 8B • Updated • 29.5k • 62 -
openbmb/MiniCPM-o-4_5-awq
Any-to-Any • 9B • Updated • 703 • 12 -
openbmb/MiniCPM-V-4_5
Image-Text-to-Text • 9B • Updated • 74.3k • 1.07k -
openbmb/MiniCPM-V-4_5-gguf
Image-Text-to-Text • 8B • Updated • 20.6k • 55 -
openbmb/MiniCPM-V-4_5-int4
Image-Text-to-Text • 9B • Updated • 2.88k • 11 -
openbmb/MiniCPM-V-4_5-AWQ
Image-Text-to-Text • 9B • Updated • 3.47k • 13 -
openbmb/MiniCPM-V-4
Image-Text-to-Text • 4B • Updated • 58.9k • 462 -
openbmb/MiniCPM-V-4-gguf
Image-Text-to-Text • 4B • Updated • 1.65k • 47 -
openbmb/MiniCPM-V-4-AWQ
Image-Text-to-Text • 4B • Updated • 26 • 10 -
openbmb/MiniCPM-V-4-int4
Image-Text-to-Text • 4B • Updated • 236 • 7 -
openbmb/MiniCPM-o-2_6
Any-to-Any • 9B • Updated • 95.9k • 1.28k -
openbmb/MiniCPM-o-2_6-gguf
Any-to-Any • 8B • Updated • 3.06k • 115 -
openbmb/MiniCPM-o-2_6-int4
Any-to-Any • Updated • 424 • 52 -
openbmb/MiniCPM-V-2_6
Image-Text-to-Text • 8B • Updated • 89.3k • 1.03k -
openbmb/MiniCPM-Llama3-V-2_5
Image-Text-to-Text • 9B • Updated • 49.4k • 1.41k -
openbmb/MiniCPM-V-2
Visual Question Answering • 3B • Updated • 58.7k • 489 -
openbmb/MiniCPM-Llama3-V-2_5-gguf
Updated • 2.44k • 216 -
openbmb/MiniCPM-V
Visual Question Answering • 3B • Updated • 659 • 196 -
openbmb/OmniLMM-12B
Visual Question Answering • Updated • 120 • 72 -
openbmb/VisCPM-Paint
Updated • 38 • 13 -
openbmb/VisCPM-Chat
Feature Extraction • Updated • 32 • 21 -
openbmb/RLAIF-V-12B
Text Generation • 12B • Updated • 12 • 7 -
openbmb/RLAIF-V-7B
Text Generation • 7B • Updated • 46 • 11 -
openbmb/MiniCPM-V-2_6-gguf
8B • Updated • 4.13k • 172 -
openbmb/MiniCPM-V-2_6-int4
Image-Text-to-Text • 8B • Updated • 6.92k • 87 -
openbmb/MiniCPM-Llama3-V-2_5-int4
Visual Question Answering • 9B • Updated • 771 • 76