Model Card for SpaceQwen2.5-VL-3B-Instruct

SpaceQwen2.5-VL-3B-Instruct uses LoRA to fine-tune Qwen2.5-VL-3B-Instruct on a dataset designed with VQASynth to enhance spatial reasoning as in SpatialVLM

Model Details

Model Description

This model uses data synthesis techniques and publically available models to reproduce the work described in SpatialVLM to enhance the spatial reasoning of multimodal models. With a pipeline of expert models, we can infer spatial relationships between objects in a scene to create VQA dataset for spatial reasoning.

• Developed by: remyx.ai
• Model type: MultiModal Model, Vision Language Model, Qwen2.5-VL-3B-Instruct
• License: Apache-2.0
• Finetuned from model: LLaVA

Model Sources

• Dataset: SpaceLLaVA
• Repository: VQASynth
• Paper: SpatialVLM

Uses

Install qwen dependencies:

pip install qwen-vl-utils[decord]==0.0.8

To run inference with this model, run:

from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "remyxai/SpaceQwen2.5-VL-3B-Instruct", torch_dtype="auto", device_map="auto"
)
processor = AutoProcessor.from_pretrained("remyxai/SpaceQwen2.5-VL-3B-Instruct")

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "https://raw.githubusercontent.com/remyxai/VQASynth/refs/heads/main/assets/warehouse_sample_2.jpeg",
            },
            {"type": "text", "text": "What is the height of the man in the red hat in feet?"},
        ],
    }
]

# 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)

Or try it with llama.cpp:

./llama-qwen2vl-cli -m /path/to/SpaceQwen2.5-VL-3B-Instruct/SpaceQwen2.5-VL-3B-Instruct-F16.gguf \
                    --mmproj /path/to/SpaceQwen2.5-VL-3B-Instruct/spaceqwen2.5-vl-3b-instruct-vision.gguf \
                    -p "What's the height of the man in the red hat?" \
                    --image /path/to/warehouse_sample_2.jpeg --threads 24 -ngl 99

You can also try it on Discord or the HF space.

Citation

@article{chen2024spatialvlm,
  title = {SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities},
  author = {Chen, Boyuan and Xu, Zhuo and Kirmani, Sean and Ichter, Brian and Driess, Danny and Florence, Pete and Sadigh, Dorsa and Guibas, Leonidas and Xia, Fei},
  journal = {arXiv preprint arXiv:2401.12168},
  year = {2024},
  url = {https://arxiv.org/abs/2401.12168},
}

@misc{qwen2.5-VL,
    title = {Qwen2.5-VL},
    url = {https://qwenlm.github.io/blog/qwen2.5-vl/},
    author = {Qwen Team},
    month = {January},
    year = {2025}
}