git clone https://github.com/RanchiZhao/AutoGPTQ.git && cd AutoGPTQ
git checkout minicpmo

# install AutoGPTQ
pip install -vvv --no-build-isolation -e .

Usage of MiniCPM-o-2_6-int4

Change the model initialization part to AutoGPTQForCausalLM.from_quantized

python

import torch
from transformers import AutoModel, AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM

model = AutoGPTQForCausalLM.from_quantized(
    'openbmb/MiniCPM-o-2_6-int4',
    torch_dtype=torch.bfloat16,
    device="cuda:0",
    trust_remote_code=True,
    disable_exllama=True,
    disable_exllamav2=True
)
tokenizer = AutoTokenizer.from_pretrained(
    'openbmb/MiniCPM-o-2_6-int4',
    trust_remote_code=True
)

model.init_tts()