Update README.md

README.md

@@ -17,7 +17,7 @@ We are thrilled to introduce Seed-Coder, a powerful, transparent, and parameter-
   <img width="100%" src="imgs/seed-coder_intro_performance.jpg">
 </p>
 
-This repo contains Seed-Coder-8B-Base model, which has the following features:
+This repo contains Seed-Coder-8B-Reasoning model, which has the following features:
 - Type: Causal Language Models
 - Data source: Public Dataset
 - Training Stage: Pretraining & Post-training
@@ -27,8 +27,7 @@ This repo contains Seed-Coder-8B-Base model, which has the following features:
 ## Highlight
 
 **Seed-Coder-8B-Reasoning** is an 8-billion-parameter model further optimized for **code reasoning**, **problem-solving**, and **algorithmic thinking** tasks.  
-- Trained on a **massively curated corpus**, filtered using an **LLM-based method** to ensure high-quality real-world code, text-code alignment, and synthetic datasets.
-- **Sandbox fine-tuning** to specifically strengthen **multi-step reasoning**, **algorithm design**, and **competitive programming** capabilities.
+- **Reinforcement Learning** to specifically strengthen **multi-step reasoning**, **algorithm design**, and **competitive programming** capabilities.