Update README.md

README.md

@@ -3,7 +3,7 @@ license: apache-2.0
 pipeline_tag: text-generation
 library_name: transformers
 base_model:
-- open-thoughts/OpenThinker-Agent-v1
+- Qwen/Qwen3-8B
 datasets:
 - DedeProGames/Terminal-Reasoning-SFT
 tags:
@@ -53,4 +53,4 @@ OpenAgent is designed to improve performance on terminal-based reasoning, softwa
 - **Model:** [`DedeProGames/OpenAgent`](https://huggingface.co/DedeProGames/OpenAgent)
 - **Dataset:** [`DedeProGames/Terminal-Reasoning-SFT`](https://huggingface.co/datasets/DedeProGames/Terminal-Reasoning-SFT)
 
-OpenAgent is an open-source effort focused on building stronger agentic models through better datasets, practical training, and real benchmark evaluation.
+OpenAgent is an open-source effort focused on building stronger agentic models through better datasets, practical training, and real benchmark evaluation.