Enhance model card: Metadata, links, and usage example

This PR significantly improves the model card for **SpatialThinker-7B** by adding crucial metadata, relevant external links, and a practical usage example.

Specifically, it addresses the following:
- **Adds metadata**: Sets `license: apache-2.0`, `library_name: transformers` (enabling automated code snippets), and `pipeline_tag: image-text-to-text` (improving discoverability for multimodal tasks).
- **Updates content**: Replaces placeholder text with the paper's abstract, a detailed model description, and relevant sections from the GitHub README (Updates, Requirements, Installation, Training, Evaluation, Acknowledgements).
- **Includes links**: Adds direct links to the Hugging Face paper page ([SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards](https://huggingface.co/papers/2511.07403)), the project page (`https://hunarbatra.com/SpatialThinker/`), and the GitHub repository (`https://github.com/hunarbatra/SpatialThinker`).
- **Provides a usage example**: Adds a clear Python code snippet demonstrating how to load and use the model with the `transformers` library for image-text inference, derived from common `transformers` patterns for QwenVL models and the overall context.

These enhancements will make the model more accessible, discoverable, and easier to use for the Hugging Face community.

README.md

@@ -1,203 +1,241 @@
 ---
-datasets:
-- OX-PIXL/STVQA-7K
 base_model:
 - Qwen/Qwen2.5-VL-7B-Instruct
+datasets:
+- OX-PIXL/STVQA-7K
+license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
 ---
 
-Paper: https://arxiv.org/abs/2511.07403
+# SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
 
-# Model Card for Model ID
+<p align="center">
+  <a href="https://huggingface.co/papers/2511.07403">
+    <img src="https://img.shields.io/badge/Paper-2511.07403-b31b1b.svg" alt="Paper">
+  </a>
+  <a href="https://hunarbatra.com/SpatialThinker">
+    <img src="https://img.shields.io/badge/🌐%20Project%20Page-blue.svg" alt="Project Page">
+  </a>
+  <a href="https://github.com/hunarbatra/SpatialThinker">
+    <img src="https://img.shields.io/badge/GitHub%20Repo-black?logo=github" alt="GitHub Repo">
+  </a>
+  <a href="https://huggingface.co/collections/OX-PIXL/spatialthinker">
+    <img src="https://img.shields.io/badge/🤗%20Models%20%26%20Dataset-orange.svg" alt="Hugging Face Models">
+  </a>
+</p>
 
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
+## Model Description
 
-### Model Description
+Multimodal large language models (MLLMs) have achieved remarkable progress in vision–language tasks, but they continue to struggle with spatial understanding. Existing spatial MLLMs often rely on explicit 3D inputs or architecture-specific modifications, and remain constrained by large-scale datasets or sparse supervision. To address these limitations, we introduce **SpatialThinker**, a 3D-aware MLLM trained with RL to integrate structured spatial grounding with multi-step reasoning. The model simulates human-like spatial perception by constructing a scene graph of task-relevant objects and spatial relations, and reasoning towards an answer via dense spatial rewards.
 
-<!-- Provide a longer summary of what this model is. -->
+**SpatialThinker** consists of two key contributions:
+1.  A data synthesis pipeline that generates **STVQA-7K**, a high-quality spatial VQA dataset.
+2.  Online RL with a multi-objective dense spatial reward enforcing spatial grounding.
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+**SpatialThinker-7B** outperforms supervised fine-tuning and the sparse RL baseline on spatial understanding and real-world VQA benchmarks, nearly doubling the base-model gain compared to sparse RL, and surpassing GPT-4o. These results showcase the effectiveness of combining spatial supervision with reward-aligned reasoning in enabling robust 3D spatial understanding with limited data and advancing MLLMs towards human-level visual reasoning.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+<p align="center">
+  <img src="https://github.com/hunarbatra/SpatialThinker/raw/main/assets/spatialthinker.jpg" width="60%" alt="SpatialThinker Overview">
+</p>
 
-### Model Sources [optional]
+## Model Details
 
-<!-- Provide the basic links for the model. -->
+*   **Developed by:** Hunar Batra, Haoqin Tu, Hardy Chen, Yuanze Lin, Cihang Xie, Ronald Clark
+*   **Model type:** 3D-aware Multimodal Large Language Model (MLLM)
+*   **Language(s) (NLP):** English
+*   **License:** Apache-2.0
+*   **Finetuned from model:** [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+### Model Sources
 
-## Uses
+*   **Repository:** [https://github.com/hunarbatra/SpatialThinker](https://github.com/hunarbatra/SpatialThinker)
+*   **Paper:** [https://huggingface.co/papers/2511.07403](https://huggingface.co/papers/2511.07403)
+*   **Project Page:** [https://hunarbatra.com/SpatialThinker/](https://hunarbatra.com/SpatialThinker/)
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+## How to Get Started with the Model
 
-### Direct Use
+This model can be loaded and used directly with the Hugging Face `transformers` library.
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+First, ensure you have the necessary dependencies installed:
 
-[More Information Needed]
+```bash
+pip install transformers>=4.49.0
+pip install flash-attn>=2.4.3 vllm>=0.7.3 # (vllm 0.8.0 recommended)
+```
 
-### Downstream Use [optional]
+Then, you can use the following Python code snippet for inference:
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+```python
+import torch
+from transformers import AutoProcessor, AutoModelForCausalLM
+from PIL import Image
+import requests
+from io import BytesIO
 
-[More Information Needed]
+# Load model and processor
+model_id = "OX-PIXL/SpatialThinker-7B" # This is the model repository ID
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16, # Use bfloat16 for better performance on compatible GPUs
+    device_map="auto",
+    trust_remote_code=True # Required for custom Qwen2.5-VL architecture
+).eval() # Set model to evaluation mode
 
-### Out-of-Scope Use
+# Example image (replace with your own image path or URL)
+image_url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg"
+response = requests.get(image_url)
+image = Image.open(BytesIO(response.content)).convert("RGB")
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+# Define a spatial reasoning question
+question = "What are the spatial relationships between the car, the road, and the trees?"
 
-[More Information Needed]
+# Construct chat messages
+messages = [
+    {"role": "user", "content": [
+        {"type": "image", "image": image},
+        {"type": "text", "text": question}
+    ]}
+]
 
-## Bias, Risks, and Limitations
+# Apply chat template and process inputs
+prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+# Generate response
+with torch.no_grad():
+    output_ids = model.generate(**inputs, max_new_tokens=512, do_sample=False) # Use suitable generation parameters
+response_text = processor.decode(output_ids[0], skip_special_tokens=True)
 
-[More Information Needed]
+print(f"Question: {question}
+")
+print(f"Answer: {response_text}")
+```
 
-### Recommendations
+## Updates
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+*   **[2025/11/11]** 🔥 Code base released.
+*   **[2025/11/08]** 🔥 Model Checkpoints and Dataset released.
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+## Requirements
 
-## How to Get Started with the Model
+*   Python 3.9+
+*   `transformers >= 4.49.0`
+*   `flash-attn >= 2.4.3`
+*   `vllm >= 0.7.3` (0.8.0 recommended)
 
-Use the code below to get started with the model.
+## Installation
 
-[More Information Needed]
+```bash
+pip install -e .
+```
 
 ## Training Details
 
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
 ### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
+SpatialThinker models are trained with STVQA-7K, Dense Spatial Rewards + GRPO. Baseline models (Vanilla GRPO) are also trained with STVQA-7K.
 
+#### Train **SpatialThinker Models** with STVQA-7K, Dense Spatial Rewards + GRPO
 
-#### Training Hyperparameters
+```bash
+bash scripts/spatialthinker_3b_grpo.sh
+bash scripts/spatialthinker_7b_grpo.sh
+```
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+#### Train **Baseline Models** (Vanilla GRPO) with STVQA-7K
 
-#### Speeds, Sizes, Times [optional]
+```bash
+bash scripts/qwen_2_5_3b_stvqa_vanilla_grpo.sh
+bash scripts/qwen_2_5_7b_stvqa_vanilla_grpo.sh
+```
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+### Merge Checkpoints to Hugging Face Format
 
-[More Information Needed]
+```bash
+python3 scripts/model_merger.py --local_dir path_to_your_last_actor_checkpoint
+```
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in Lacoste et al. (2019).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+To evaluate **SpatialThinker** or baseline models across spatial reasoning benchmarks, use the provided `evaluation/eval.py` script.
+
+### Basic Command Structure
+
+```bash
+python3 evaluation/eval.py \
+    --dataset <dataset_name> \
+    --template <prompt_template> \ # e.g. `reasoning`, `no_reasoning`, `spatial_thinker`  
+    --model_path <model_or_checkpoint> \
+    --cuda <gpu_id> \
+    --batch_size <num_samples_per_step> \
+    [--provider <inference_backend>] \ 
+    [--processor_name <tokenizer_or_processor>] \
+    [--custom_filename <output_name>]
+```
+
+### Example: Evaluate Across Multiple Benchmarks
+
+```bash
+python3 evaluation/eval.py \
+    --dataset blink-spatial \
+    --template spatial_thinker \
+    --model_path OX-PIXL/SpatialThinker-3B \
+    --cuda 0 \
+    --batch_size 4
+```
+```bash
+python3 evaluation/eval.py \
+    --dataset spatialbench \
+    --template spatial_thinker \
+    --model_path OX-PIXL/SpatialThinker-3B \
+    --cuda 0 \
+    --batch_size 2
+```
+
+### Example: Evaluate Using an API Provider (OpenAI / Anthropic)
+
+```bash
+python3 evaluation/eval.py \
+    --dataset stvqa \
+    --template reasoning \
+    --model_path gpt-4o-2024-05-13 \
+    --provider openai \
+    --batch_size 1
+```
+```bash
+python3 evaluation/eval.py \
+    --dataset stvqa \
+    --template reasoning \
+    --model_path claude-3-5-sonnet \
+    --provider anthropic \
+    --batch_size 1
+```
+
+### Supported Evaluation Datasets
+`cv-bench`, `cv-bench-2D`, `cv-bench-3D`, `blink-spatial`, `blink-depth`, `blink-object`,  
+`blink-counting`, `blink-multi-view`, `blink-jigsaw`, `realworld_qa`, `spatialbench`, `mmvp`, `3dsrbench`,
+`lego`, `spatialreasoner`, `robospatial`, `robospatial_rgb`, `stvqa`, `hallusionbench`.
+
+## Citation
+
+If you find this repository useful in your project, please consider giving a ⭐ and citing:
+
+```bibtex
+@misc{batra2025spatialthinkerreinforcing3dreasoning,  
+	title={SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards},  
+	author={Hunar Batra and Haoqin Tu and Hardy Chen and Yuanze Lin and Cihang Xie and Ronald Clark},  
+	year={2025},  
+	eprint={2511.07403},  
+	archivePrefix={arXiv},  
+	primaryClass={cs.CV},  
+	url={https://arxiv.org/abs/2511.07403},  
+}
+```
+
+## Acknowledgements
+This project builds upon the following open-source frameworks and works:
+-   [**EasyR1**](https://github.com/hiyouga/EasyR1) — An efficient, scalable, multi-modality RL training framework based on veRL  
+-   [**LLaMA-Factory**](https://github.com/hunarbatra/LLaMA-Factory) — Unified efficient fine-tuning of 100+ LLMs & VLMs  
+-   [**Qwen2.5-VL**](https://arxiv.org/abs/2502.13923) — Multimodal LLM series from the Qwen family