Correct pipeline tag and add library name

This PR corrects the pipeline tag to `text-generation` and adds the `library_name` to ensure the model can be found via the right pipeline and used with the Transformers library.

README.md

@@ -1,10 +1,11 @@
 ---
-license: apache-2.0
-datasets:
-- TIGER-Lab/WebInstruct-verified
 base_model:
 - Qwen/Qwen3-4B-Base
-pipeline_tag: question-answering
+datasets:
+- TIGER-Lab/WebInstruct-verified
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
 ---
 
 # General-Reasoner: Advancing LLM Reasoning Across All Domains
@@ -17,8 +18,6 @@ pipeline_tag: question-answering
   <a href="https://tiger-ai-lab.github.io/General-Reasoner/" target="_blank">🌐 Project Page</a>
 </p>
 
-
-
 ## Overview
 
 <p align="center">
@@ -37,8 +36,7 @@ pipeline_tag: question-answering
 - **Diverse Reasoning Data:** 230K+ high-quality, verifiable questions sourced from the web and filtered for answer verifiability across disciplines.
 - **Model-Based Verifier:** Compact 1.5B generative verifier model for context-aware, chain-of-thought answer validation, outperforming traditional rule-based methods.
 
-**This specific model is the General-Reasoner variant trained based on [Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base).**
-
+**This specific model is the General-Reasoner variant trained based on [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base).**
 
 ## Main Results
 General-Reasoner outperforms base and supervised models on a variety of reasoning benchmarks, demonstrating robust generalization across domains: