Update README.md

README.md

@@ -1,6 +1,7 @@
 ---
 license: apache-2.0
-base_model: NousResearch/NousCoder-14B
+base_model:
+- Qwen/Qwen3-14B
 pipeline_tag: text-generation
 library_name: transformers
 tags:
@@ -10,15 +11,19 @@ tags:
 - safetensors
 ---
 
-# GRM-Coder-14b
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/685ea8ff7b4139b6845ce395/YF0kEDYMGJhcM3Lbl2EOD.png" alt="logo" width="250">
+</p>
 
-Espelho / republicação de `NousResearch/NousCoder-14B` em `OrionLLM/GRM-Coder-14b`.
+<p align="center"><b>A powerful 14B coding model designed for competitive programming.</b></p>
 
-## Origem
-- Modelo original: `NousResearch/NousCoder-14B`
+---
+
+This is a coding model based on Qwen3-14B for competitive programming.  
+On LiveCodeBench v6 (08/01/2024 - 05/01/2025), we achieve a Pass@1 accuracy of **67.87%**, up **7.08%** from the baseline Pass@1 accuracy of **60.79%** of Qwen3-14B.  
+We trained on **24k verifiable coding problems** using **48 B200 GPUs** over the course of four days.
 
-## Licença
-Este repositório segue a licença do modelo original: **Apache-2.0**.
+---
 
-## Observação
-Os pesos foram espelhados para este repositório com preservação de atribuição ao modelo original.
+![test](./lcb_score_vs_step.png)  
+![test](./performance_params_ratio.png)