🚀 A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

A powerful MLLM that can handle single image, multi - image, and video tasks, comparable to GPT - 4V level, and can run on your phone.

GitHub | Demo

📢 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

MiniCPM-V 2.6 is the latest and most capable model in the MiniCPM-V series. Built on SigLip-400M and Qwen2-7B with a total of 8B parameters, it shows a significant performance improvement over MiniCPM-Llama3-V 2.5 and introduces new features for multi-image and video understanding. The notable features are as follows:

• 🔥 Leading Performance. MiniCPM-V 2.6 achieves an average score of 65.2 on the latest version of OpenCompass, a comprehensive evaluation over 8 popular benchmarks. With only 8B parameters, it surpasses widely used proprietary models like GPT-4o mini, GPT-4V, Gemini 1.5 Pro, and Claude 3.5 Sonnet for single image understanding.

• 🖼️ Multi Image Understanding and In-context Learning. MiniCPM-V 2.6 can also perform conversation and reasoning over multiple images. It achieves state-of-the-art performance on popular multi-image benchmarks such as Mantis-Eval, BLINK, Mathverse mv and Sciverse mv, and also shows promising in-context learning capability.

• 🎬 Video Understanding. MiniCPM-V 2.6 can also accept video inputs, performing conversation and providing dense captions for spatial-temporal information. It outperforms GPT-4V, Claude 3.5 Sonnet and LLaVA-NeXT-Video-34B on Video-MME with/without subtitles.

• 💪 Strong OCR Capability and Others. MiniCPM-V 2.6 can process images with any aspect ratio and up to 1.8 million pixels (e.g., 1344x1344). It achieves state-of-the-art performance on OCRBench, surpassing proprietary models such as GPT-4o, GPT-4V, and Gemini 1.5 Pro. Based on the latest RLAIF-V and VisCPM techniques, it features trustworthy behaviors, with significantly lower hallucination rates than GPT-4o and GPT-4V on Object HalBench, and supports multilingual capabilities on English, Chinese, German, French, Italian, Korean, etc.

• 🚀 Superior Efficiency. In addition to its friendly size, MiniCPM-V 2.6 also shows state-of-the-art token density (i.e., number of pixels encoded into each visual token). It produces only 640 tokens when processing a 1.8M pixel image, which is 75% fewer than most models. This directly improves the inference speed, first-token latency, memory usage, and power consumption. As a result, MiniCPM-V 2.6 can efficiently support real-time video understanding on end-side devices such as iPad.

• 💫 Easy Usage. MiniCPM-V 2.6 can be easily used in various ways: (1) llama.cpp and ollama support for efficient CPU inference on local devices. (2) int4 and GGUF format quantized models in 16 sizes. (3) vLLM support for high-throughput and memory-efficient inference. (4) Fine-tuning on new domains and tasks. (5) Quick local WebUI demo setup with Gradio. (6) Online web demo.

📊 Evaluation

Single image results on OpenCompass, MME, MMVet, OCRBench, MMMU, MathVista, MMB, AI2D, TextVQA, DocVQA, HallusionBench, Object HalBench:

Multi-image results on Mantis Eval, BLINK Val, Mathverse mv, Sciverse mv, MIRB:

Video results on Video-MME and Video-ChatGPT:

🌟 Examples

Click to view more cases.

🎮 Demo

Click here to try the Demo of MiniCPM-V 2.6.

💻 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
decord

🔍 Basic Usage

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

model = AutoModel.from_pretrained('openbmb/MiniCPM-V-2_6', trust_remote_code=True,
    attn_implementation='sdpa', torch_dtype=torch.bfloat16) # sdpa or flash_attention_2, no eager
model = model.eval().cuda()
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-2_6', trust_remote_code=True)

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,
    stream=True
)

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

💬 Chat with multiple images

</details>

### 📚 In-context few-shot learning
<details>
<summary> Click to view Python code running MiniCPM-V 2.6 with few-shot input. </summary>
```python
import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained('openbmb/MiniCPM-V-2_6', trust_remote_code=True,
    attn_implementation='sdpa', torch_dtype=torch.bfloat16) # sdpa or flash_attention_2, no eager
model = model.eval().cuda()
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-2_6', trust_remote_code=True)

question = "production date" 
image1 = Image.open('example1.jpg').convert('RGB')
answer1 = "2023.08.04"
image2 = Image.open('example2.jpg').convert('RGB')
answer2 = "2007.04.24"
image_test = Image.open('test.jpg').convert('RGB')

msgs = [
    {'role': 'user', 'content': [image1, question]}, {'role': 'assistant', 'content': [answer1]},
    {'role': 'user', 'content': [image2, question]}, {'role': 'assistant', 'content': [answer2]},
    {'role': 'user', 'content': [image_test, question]}
]

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

🎥 Chat with video

vr = VideoReader(video_path, ctx=cpu(0))
sample_fps = round(vr.get_avg_fps() / 1)  # FPS
frame_idx = [i for i in range(0, len(vr), sample_fps)]
if len(frame_idx) > MAX_NUM_FRAMES:
    frame_idx = uniform_sample(frame_idx, MAX_NUM_FRAMES)
frames = vr.get_batch(frame_idx).asnumpy()
frames = [Image.fromarray(v.astype('uint8')) for v in frames]
print('num frames:', len(frames))
return frames

| Property | Details |
|----------|---------|
| Pipeline Tag | image-text-to-text |
| Datasets | openbmb/RLAIF-V-Dataset |
| Library Name | transformers |
| Language | multilingual |
| Tags | minicpm-v, vision, ocr, multi-image, video, custom_code |