README.md

---
library_name: transformers
tags: []
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

## Uses


    from transformers import AutoProcessor, AutoModel  
    import torch
    from PIL import Image
    
    model = AutoModel.from_pretrained('princepride/MiniCPM-V-2_6-VPM', trust_remote_code=True,
    attn_implementation='flash_attention_2', torch_dtype=torch.bfloat16)
    processor = AutoProcessor.from_pretrained('princepride/MiniCPM-V-2_6-VPM', trust_remote_code=True)
    image = Image.open(r'workspace/00002-2654981627.png').convert('RGB')

    
    inputs = processor(
            [image], 
            max_slice_nums=max_slice_nums,
            use_image_id=use_image_id,
            return_tensors="pt", 
            max_length=max_inp_length
        )
    model(inputs)
    model = model.eval().cuda()