Create README.md

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+language:
+- en
+- zh
+pipeline_tag: image-text-to-text
+tags:
+- remote-sensing
+- geospatial-reasoning
+- qwen2.5-vl
+- sft
+- chain-of-thought
+- ms-swift
+---
+
+# LandAI-Base: Activating Geospatial Chain-of-Thought Reasoning
+
+<div align="center">
+
+**[Paper (Under Review)]** 
+
+</div>
+
+## 📖 Introduction
+
+**LandAI-Base** is the foundational **Supervised Fine-Tuned (SFT)** model of the LandAI family. Built upon the **Qwen2.5-VL-7B-Instruct** architecture, it is specifically designed to activate domain-specific logical reasoning in Earth Observation tasks.
+
+Unlike general-purpose multimodal models, LandAI-Base has been fine-tuned on a composite corpus of approximately **334,000 reasoning chains**, including the novel **Geo-Base-Thinking-14K** dataset. This process instills the model with the "epistemological authority" of geography experts, enabling it to decompose complex spatial problems before engaging in visual recognition.
+
+**LandAI-Base serves two primary purposes:**
+1.  **A robust baseline** for geospatial reasoning tasks (Q&A, analysis).
+2.  **The "Cold Start" initialization** for the [LandAI-L1](https://huggingface.co/zhou777/LandAI-L1) model (trained via GRPO-L1).
+
+## 🚀 Key Features
+
+* **Domain-Specific Cognitive Activation**: Fine-tuned to simulate the reasoning patterns of geography experts, moving from rote memorization to logical deduction.
+* **High-Quality Training Data**: Trained on a curated mix of:
+    * **Geo-Base-Thinking-14K**: ~14.7k distillations from geography entrance exams and textbooks.
+    * **General Reasoning Corpus**: Subsets from OpenR1-Math, OpenThoughts, and Chinese-Data-R1 to enhance mathematical and scientific logic.
+* **Strong Zero-Shot Performance**: Significantly outperforms the vanilla Qwen2.5-VL-7B on geographic benchmark exams.
+* **MS-Swift Compatibility**: Fully compatible with the [ms-swift](https://github.com/modelscope/swift) training framework.
+
+## 📊 Performance Benchmarks
+
+LandAI-Base demonstrates a substantial leap in reasoning capabilities compared to its backbone model. In the **GeoTest2025** benchmark (derived from restricted 2025 National Postgraduate Entrance Examination questions), it achieves near-commercial performance.
+
+| Model | GeoTest2025 (Geography) | AIME 2024 (Math Logic) | HumanEval | MMMU pro |
+| :--- | :---: | :---: | :---: |
+| **LandAI-Base-7B (Ours)** | **93.3%** | **16.7%** | **66.4%** | **44.7%** |
+| Qwen2.5-VL-7B (Baseline) | 46.7% | 3.3% | 67.3% | 41.2% |
+| GPT-4o | 92.1% | 9.3% | 90.2% | 51.9% |
+| Gemini 2.5 Pro | 98.3% | 92.0% | - | 71.2% |
+
+> **Note**: As shown in Extended Data Table 2 of the paper, LandAI-Base achieves a **2.5x improvement** in geographic reasoning and a **5x improvement** in mathematical logic over the vanilla baseline.
+
+## 📂 Dataset Composition
+
+The explicit reasoning capability of LandAI-Base stems from its training data distribution:
+
+| Dataset Source | Samples | Purpose |
+| :--- | :--- | :--- |
+| **Geo-Base-Thinking-14K** | ~14.7k | Domain-specific geospatial logic & knowledge |
+| **OpenR1-Math** | ~96k | Mathematical reasoning infrastructure |
+| **OpenThoughts** | ~114k | General scientific literacy (Physics/Chem/Bio) |
+| **Chinese-Data-R1** | ~110k | Linguistic nuance and logic bridging |
+
+## 🛠️ Quick Start
+
+LandAI-Base follows the standard **Qwen2.5-VL** architecture. You can use it for geospatial Question Answering or as a base for further RL training.
+