# this is very similar to qwen2-vl
from slimm.model.processor import SliMMQwen2VLProcessor
from slimm.model.slimm import SliMMForConditionalGeneration
from slimm.model.utils_vl import process_vision_info

model_path = "SliMM-X/CoMP-MM-1B"

model = SliMMForConditionalGeneration.from_pretrained(
    model_path, torch_dtype="auto", device_map="cuda"
)
processor = SliMMQwen2VLProcessor.from_pretrained(model_path)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://slimm-x.github.io/comp/figs/teaser.png",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

# Preparation for inference
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

Citation

BibTeX:

bibtex

@article{comp2025,
      title={CoMP: Continual Multimodal Pre-training for Vision Foundation Models}, 
      author={Chen, Yitong and Meng, Lingchen and Peng, Wujian and Wu, Zuxuan and Jiang, Yu-Gang},
      year={2025},
      journal={arXiv preprint arXiv:2503.18931}, 
}