MiniCPM-V surpasses proprietary models such as GPT-4V, Gemini Pro, Qwen-VL and Claude 3 in overall performance, and support multimodal conversation for over 30 languages.
45.6K Pulls 8 Tags Updated 1 year ago
MiniCPM-V 2.6 is the latest and most capable model in the MiniCPM-V series. It exhibits a significant performance improvement over MiniCPM-Llama3-V 2.5
32.8K Pulls 1 Tag Updated 1 year ago
MiniCPM-V是面向图文理解的端侧多模态大模型系列，该系列模型接受图像和文本输入，并提供高质量的文本输出。
5,103 Pulls 1 Tag Updated 1 year ago
from sayhan/MiniCPM-3B-OpenHermes-2.5-v2-GGUF
195 Pulls 1 Tag Updated 2 years ago
from gmonsoon/MiniCPM-3B-Turangga-v3-ep50-GGUF
91 Pulls 1 Tag Updated 2 years ago
openbmb/MiniCPM-Llama3-V-2_5
2,563 Pulls 2 Tags Updated 1 year ago
From https://modelscope.cn/models/OpenBMB/MiniCPM-Llama3-V-2_5
465 Pulls 1 Tag Updated 1 year ago
Quantized Mistral 7B Instruct models optimized for fast, CPU-only local inference with Ollama. Multiple variants balancing speed, quality, and memory efficiency.
651 Pulls 3 Tags Updated 4 months ago
(UNOFFICIAL) Ported from https://huggingface.co/OuteAI/Lite-Mistral-150M-v2-Instruct-GGUF
41 Pulls 1 Tag Updated 1 year ago