Add metadata and improve model card

README.md

@@ -1,5 +1,20 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+base_model: Qwen/Qwen3-8B
+tags:
+- reasoning
+- question-generation
+- test-time-scaling
+---
+
+# CoDiQ-Gen-8B
+
 The official repository for the paper ["CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation"](https://arxiv.org/pdf/2602.01660)
 
+Code: [GitHub - ALEX-nlp/CoDiQ](https://github.com/ALEX-nlp/CoDiQ)
+
 ## 💡 Introduction
 
 Large Reasoning Models (LRMs) benefit substantially from training on challenging, competition-level questions. However, existing automated synthesis methods struggle with **"fake hard"** questions—problems that are complex but unsolvable or ill-defined.
@@ -13,6 +28,21 @@ Key innovations include:
 
 Training LRMs on CoDiQ-Corpus substantially enhances downstream reasoning performance. The [CoDiQ-Generator](https://huggingface.co/AleXGroup/CoDiQ-Gen-8B) and [CoDiQ-Corpus](https://huggingface.co/datasets/AleXGroup/CoDiQ-Corpus) are released.
 
+## 🛠️ Quick Start
+
+### Installation
+```bash
+git clone https://github.com/ALEX-nlp/CoDiQ.git
+cd CoDiQ
+pip install -r requirements.txt
+```
+
+### Inference: Generating Difficult Questions
+
+You can leverage `CoDiQ-Gen-8B` to enhance the complexity of any seed problem. To begin, update the configuration in `tools_api.py`, `codiq_api.py`, `count_tokens.py` and then execute the following script:
+```bash
+bash run.sh
+```
 
 ## 📖 Citation