AI Agent Hub
Back to models
MiniCPM-V-2_6-int4 logo

MiniCPM-V-2_6-int4

Multimodal openbmb Released 2024-08-06
-- 8.0B params 32.8K context Open Source

About this model

News

  • [2025.01.14] 🔥🔥 We open source MiniCPM-o 2.6, with significant performance improvement over MiniCPM-V 2.6, and support real-time speech-to-speech conversation and multimodal live streaming. Try it now.

MiniCPM-V 2.6 int4

This is the int4 quantized version of MiniCPM-V 2.6.
Running with int4 version would use lower GPU memory (about 7GB).

Usage

Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.10：

Pillow==10.1.0
torch==2.1.2
torchvision==0.16.2
transformers==4.40.0
sentencepiece==0.1.99
accelerate==0.30.1
bitsandbytes==0.43.1

# test.py
import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained('openbmb/MiniCPM-V-2_6-int4', trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-2_6-int4', trust_remote_code=True)
model.eval()

image = Image.open('xx.jpg').convert('RGB')
question = 'What is in the image?'
msgs = [{'role': 'user', 'content': [image, question]}]

res = model.chat(
    image=None,
    msgs=msgs,
    tokenizer=tokenizer
)
print(res)

## if you want to use streaming, please make sure sampling=True and stream=True
## the model.chat will return a generator
res = model.chat(
    image=None,
    msgs=msgs,
    tokenizer=tokenizer,
    sampling=True,
    temperature=0.7,
    stream=True
)

generated_text = ""
for new_text in res:
    generated_text += new_text
    print(new_text, flush=True, end='')

Benchmark Scores

MMMU
49.8

Technical Specs

  • Parameters: 8.0B
  • Architecture: SigLip-400M + Qwen2-7B Transformer
  • Context Window: 32,768 tokens
  • Input Modalities: text, image

Hardware Requirements

  • VRAM: 7.0 GB
  • Compute: NVIDIA GPU with ~7GB VRAM for INT4 inference; GGUF CPU variant needs ~6GB RAM