Update README.md

README.md

@@ -70,7 +70,7 @@ print(output["generated_text"])
 
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/zhangjiayi/huggingface/runs/ukmal5l5) 
 
-This model was trained based on [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) using GRPO with rule-based RM and LLM-based RM ([Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)) and was prompted to answer a series of specific, instruction-related yes/no questions to assess the quality of rollouts, e.g.,:
+This model was trained based on [Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) using GRPO with rule-based RM and LLM-based RM ([Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)) and was prompted to answer a series of specific, instruction-related yes/no questions to assess the quality of rollouts.
 
 Specifically, there are reward functions: