Improve model card: Add pipeline tag, library name, and prominent GitHub link

This PR enhances the model card for `xl-zhao/PromptCoT-2.0-Prompt-Generation-Model` by:

* Adding `pipeline_tag: text-generation` for better discoverability on the Hub.
* Adding `library_name: transformers` to enable the automated "Use in Transformers" widget with code snippets.
* Making the GitHub repository link `https://github.com/inclusionAI/PromptCoT` more prominent by adding it directly under the model title.

These updates improve the model's visibility and usability on the Hugging Face Hub.

README.md

@@ -1,28 +1,33 @@
----
-license: mit
-language:
-- en
-base_model:
-- Qwen/Qwen2.5-32B
----
+---
+base_model:
+- Qwen/Qwen2.5-32B
+language:
+- en
+license: mit
+pipeline_tag: text-generation
+library_name: transformers
+---
+
 # PromptCoT 2.0 — Problem Generation Model
 
 This repository hosts the **Problem Generation Model (PGM)** used in [**PromptCoT 2.0**](https://arxiv.org/abs/2509.19894), a framework for **scalable prompt synthesis** that advances LLM reasoning in **mathematics** and **programming**.
 
+Code: https://github.com/inclusionAI/PromptCoT
+
 ---
 
 ## ✨ Overview
 
 This checkpoint is the **Problem Generation Model (PGM)** of PromptCoT 2.0.  
 
-- **Input:** a set of domain concepts (math or programming) and an optional difficulty tag.  
-- **Output:** a **rationale** (the structured “thinking process” that connects the concepts) **followed by** a fully formed **problem** (Olympiad-level math or coding task).  
+-   **Input:** a set of domain concepts (math or programming) and an optional difficulty tag.  
+-   **Output:** a **rationale** (the structured “thinking process” that connects the concepts) **followed by** a fully formed **problem** (Olympiad-level math or coding task).  
 
 **How it fits into PromptCoT 2.0:**  
 PromptCoT 2.0 jointly trains two models via an EM optimization loop:  
 
-- **Rationale Generator** (*E-step*): infers rationales given concepts and problems, updated via reinforcement learning with reward signals.  
-- **Problem Generation Model (PGM)** (*M-step*): learns to produce rationale–problem pairs conditioned only on concepts.  
+-   **Rationale Generator** (*E-step*): infers rationales given concepts and problems, updated via reinforcement learning with reward signals.  
+-   **Problem Generation Model (PGM)** (*M-step*): learns to produce rationale–problem pairs conditioned only on concepts.  
 
 At inference time, the PGM is all you need: provide **concepts** and it will generate **(rationale → problem)** in one pass—without any handcrafted templates or domain-specific heuristics.
 
@@ -30,10 +35,10 @@ At inference time, the PGM is all you need: provide **concepts** and it will gen
 
 ## 📦 Model Details
 
-- **Model type:** Causal language model for problem generation.  
-- **Training data:** Concept–rationale–problem triples synthesized and refined via PromptCoT 2.0.  
-- **Domains:** Mathematics (Olympiad-level) and Programming (competitive programming).  
-- **Initialization:** Warm-started from `Qwen2.5-32B-Base` with cold-start annotations (concepts & rationales) generated by instruction-tuned models.  
+-   **Model type:** Causal language model for problem generation.  
+-   **Training data:** Concept–rationale–problem triples synthesized and refined via PromptCoT 2.0.  
+-   **Domains:** Mathematics (Olympiad-level) and Programming (competitive programming).  
+-   **Initialization:** Warm-started from `Qwen2.5-32B-Base` with cold-start annotations (concepts & rationales) generated by instruction-tuned models.  
 
 ---
 
@@ -100,8 +105,8 @@ The output will first include a **Rationale** (multi-step explanation of how the
 
 The PGM is the **core component** powering the creation of:
 
-* **Self-Play datasets** (math/code problems paired with verifiable answers or unit tests).
-* **SFT datasets** (problems with complete reasoning traces distilled from teacher models).
+*   **Self-Play datasets** (math/code problems paired with verifiable answers or unit tests).
+*   **SFT datasets** (problems with complete reasoning traces distilled from teacher models).
 
 ---
 
@@ -110,28 +115,28 @@ The PGM is the **core component** powering the creation of:
 PromptCoT 2.0 demonstrates that rationale-driven prompt synthesis yields **harder and more diverse problems** than existing datasets.
 
 
-* **Self-Play (30B-A3B):**  
-  Achieves strong gains in both mathematics and programming.  
-  - **Math:** 92.1 on AIME24, 89.8 on AIME25, 76.7 on HMMT Feb25.  
-  - **Code:** 74.2 on LiveCodeBench v5, 71.0 on v6, and 2079 Elo on Codeforces.  
-  Overall, performance is competitive with Gemini 2.5 Pro / OpenAI o3 and surpasses strong open-source baselines.
+*   **Self-Play (30B-A3B):**  
+    Achieves strong gains in both mathematics and programming.  
+    -   **Math:** 92.1 on AIME24, 89.8 on AIME25, 76.7 on HMMT Feb25.  
+    -   **Code:** 74.2 on LiveCodeBench v5, 71.0 on v6, and 2079 Elo on Codeforces.  
+    Overall, performance is competitive with Gemini 2.5 Pro / OpenAI o3 and surpasses strong open-source baselines.
 
-* **SFT (7B, 100% synthetic):**  
-  Demonstrates that fully synthetic data can rival or outperform human-written datasets.  
-  - **Math:** 73.1 on AIME24, 65.6 on AIME25, 46.5 on HMMT Feb25.  
-  - **Code:** 53.4 on LiveCodeBench v5, 48.9 on v6, and 1815 Elo on Codeforces.  
-  These results exceed human-written baselines such as **OpenMathReasoning** and **OpenCodeReasoning**, highlighting the scalability of synthetic data.
+*   **SFT (7B, 100% synthetic):**  
+    Demonstrates that fully synthetic data can rival or outperform human-written datasets.  
+    -   **Math:** 73.1 on AIME24, 65.6 on AIME25, 46.5 on HMMT Feb25.  
+    -   **Code:** 53.4 on LiveCodeBench v5, 48.9 on v6, and 1815 Elo on Codeforces.  
+    These results exceed human-written baselines such as **OpenMathReasoning** and **OpenCodeReasoning**, highlighting the scalability of synthetic data.
 
 
 ---
 
 ## 📂 Resources
 
-* 📄 [Paper (arXiv:2509.19894)](https://arxiv.org/abs/2509.19894)
-* 🤗 [HF Collection](https://huggingface.co/collections/xl-zhao/promptcot-20-68d27cd73f2faef5a12f777d)
-* 📚 [PromptCoT 2.0 SFT Data (4.8M prompts)](https://huggingface.co/datasets/xl-zhao/PromptCoT-2.0-SFT-4.8M)
-* 🤖 [PromptCoT 2.0 SFT Model (7B)](https://huggingface.co/xl-zhao/PromptCoT-2.0-SFT-7B)
-* 🎮 [Self-Play Models (4B, 30B-A3B)](https://huggingface.co/collections/xl-zhao/promptcot-20-68d27cd73f2faef5a12f777d)
+*   📄 [Paper (arXiv:2509.19894)](https://arxiv.org/abs/2509.19894)
+*   🤗 [HF Collection](https://huggingface.co/collections/xl-zhao/promptcot-20-68d27cd73f2faef5a12f777d)
+*   📚 [PromptCoT 2.0 SFT Data (4.8M prompts)](https://huggingface.co/datasets/xl-zhao/PromptCoT-2.0-SFT-4.8M)
+*   🤖 [PromptCoT 2.0 SFT Model (7B)](https://huggingface.co/xl-zhao/PromptCoT-2.0-SFT-7B)
+*   🎮 [Self-Play Models (4B, 30B-A3B)](https://huggingface.co/collections/xl-zhao/promptcot-20-68d27cd73f2faef5a12f777d)
 
 ---