README.md

metadata

license: apache-2.0
datasets:
  - remyxai/OpenSpaces
tags:
  - remyx
  - vqasynth
  - spatial-reasoning
  - multimodal
  - vlm
  - vision-language
  - robotics
  - distance-estimation
  - embodied-ai
  - quantitative-spatial-reasoning
base_model:
  - Qwen/Qwen2.5-VL-3B-Instruct
language:
  - en
pipeline_tag: image-text-to-text
new_version: remyxai/SpaceThinker-Qwen2.5VL-3B
library_name: transformers

SpaceQwen2.5-VL-3B-Instruct

• Model Type: Multimodal, Vision-Language Model
• Architecture: Qwen2.5-VL-3B-Instruct
• Model Size: 3.75B parameters (FP16)
• Finetuned from: Qwen/Qwen2.5-VL-3B-Instruct
• Finetune Strategy: LoRA (Low-Rank Adaptation)
• License: Apache-2.0

Model Overview

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.

Running SpaceQwen2.5-VL-3B-Instruct

Transformers

Install qwen dependencies:

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

To run inference on a sample image:

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)

GGUF

Or run SpaceQwen2.5-VL-3B-Instruct using 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

Dataset & Training

SpaceQwen2.5-VL-3B-Instruct uses LoRA to fine-tune Qwen2.5-VL-3B-Instruct on the OpenSpaces dataset.

Dataset Summary:

• ~10k synthetic spatial reasoning traces

• Question types: spatial relations (distances (units), above, left-of, contains, closest to)

• Format: image (RGB) + question + answer

• Dataset: OpenSpaces

• Code: VQASynth

• Reference: SpatialVLM

Scripts for LoRA SFT available at trl

Model Evaluation (Coming Soon)

Stay tuned for the VLMEvalKit QSpatial benchmark

Planned comparisons:

• 🌋 SpaceLLaVA
• 🧑‍🏫 SpaceQwen2.5-VL-3B-Instruct
• 🤖 Related VLMs and VLAs for robotics

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

⚠️ Limitations & Ethical Considerations

• Performance may degrade in cluttered environments or camera perspective.
• This model was fine-tuned using synthetic reasoning over an internet image dataset.
• Multimodal biases inherent to the base model (Qwen2.5-VL) may persist.
• Not intended for use in safety-critical or legal decision-making.

Users are encouraged to evaluate outputs critically and consider fine-tuning for domain-specific safety and performance.

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}
}