Minicpm Llama3 V 2 5 Int4

🚀 MiniCPM-Llama3-V 2.5 int4

This is an int4 quantized model for visual question - answering, which can significantly reduce GPU memory usage.

🚀 Quick Start

This is the int4 quantized version of MiniCPM-Llama3-V 2.5. Running with the int4 version would use lower GPU memory (about 9GB).

📦 Installation

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

💻 Usage Examples

Basic Usage

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

model = AutoModel.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5-int4', trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5-int4', trust_remote_code=True)
model.eval()

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

res = model.chat(
    image=image,
    msgs=msgs,
    tokenizer=tokenizer,
    sampling=True, # if sampling=False, beam_search will be used by default
    temperature=0.7,
    # system_prompt='' # pass system_prompt if needed
)
print(res)

Advanced Usage

## 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=image,
    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='')

📚 Documentation