ATH-MaaS/Ovis-Clip-Qwen1_5-14B

pip install torch==2.1.0 transformers==4.41.1 deepspeed==0.14.0 pillow==10.3.0

import torch
from PIL import Image
from transformers import AutoModelForCausalLM

# load model
model = AutoModelForCausalLM.from_pretrained("AIDC-AI/Ovis-Clip-Qwen1_5-14B",
                                             torch_dtype=torch.bfloat16,
                                             multimodal_max_length=8192,
                                             trust_remote_code=True).cuda()
text_tokenizer = model.get_text_tokenizer()
visual_tokenizer = model.get_visual_tokenizer()
conversation_formatter = model.get_conversation_formatter()

# enter image path and prompt
image_path = input("Enter image path: ")
image = Image.open(image_path)
text = input("Enter prompt: ")
query = f'<image> {text}'
prompt, input_ids = conversation_formatter.format_query(query)
input_ids = torch.unsqueeze(input_ids, dim=0).to(device=model.device)
attention_mask = torch.ne(input_ids, text_tokenizer.pad_token_id).to(device=model.device)
pixel_values = [visual_tokenizer.preprocess_image(image).to(
    dtype=visual_tokenizer.dtype, device=visual_tokenizer.device)]

# print model output
with torch.inference_mode():
    kwargs = dict(
        pixel_values=pixel_values,
        attention_mask=attention_mask,
        do_sample=False,
        top_p=None,
        temperature=None,
        top_k=None,
        repetition_penalty=None,
        max_new_tokens=512,
        use_cache=True,
        eos_token_id=text_tokenizer.eos_token_id,
        pad_token_id=text_tokenizer.pad_token_id
    )
    output_ids = model.generate(input_ids, **kwargs)[0]
    input_token_len = input_ids.shape[1]
    output = text_tokenizer.decode(output_ids[input_token_len:], skip_special_tokens=True)
    print(f'Output: {output}')

@article{lu2024ovis,
  title={Ovis: Structural Embedding Alignment for Multimodal Large Language Model}, 
  author={Shiyin Lu and Yang Li and Qing-Guo Chen and Zhao Xu and Weihua Luo and Kaifu Zhang and Han-Jia Ye},
  year={2024},
  journal={arXiv:2405.20797}
}