README.md

metadata

language:
  - zh
  - en
base_model:
  - openbmb/MiniCPM-V-4
pipeline_tag: image-text-to-text
library_name: transformers
tags:
  - MiniCPM
  - MiniCPM-V-4

MiniCPM-V-4

Convert tools links:

For those who are interested in model conversion, you can try to export axmodel through the original repo : https://huggingface.co/openbmb/MiniCPM-V-4

How to Convert LLM from Huggingface to axmodel

Support Platform

• AX650
  • AX650N DEMO Board
  • M4N-Dock(爱芯派Pro)
  • M.2 Accelerator card

How to use

Download all files from this repository to the device

root@ax650:~/wangjian/minicpm-v-4# tree -L 1
.
├── embed_tokens.pth
├── minicpm-v-4_axmodel
├── minicpmv4_tokenizer
├── resampler.axmodel
├── run_axmodel.py
├── show_demo.jpg
└── siglip.axmodel

install transformers

pip install transformers==4.51.0

Inference with AX650 Host on AX650 DEMO Board

run following cmd：

python3 run_axmodel.py -i show_demo.jpg -q "What is the landform in the picture?"

input image：

minicpm-v-4 output:

question1 = "What is the landform in the picture?"

answer1 = The landform in the picture is a karst topography, characterized by its unique and dramatic appearance with steep limestone cliffs rising from the water' s surface. This type of landscape is commonly found in regions with significant geological activity, such as China's Li River.