Update README.md

README.md

@@ -42,7 +42,7 @@ This model is built on top of **[Qwen/Qwen2.5-3B-Instruct](https://huggingface.c
   - **vLLM** support via `use_vllm = True` for efficient inference
 
 ## Dataset
-- The training script loads a **custom JSON file** (`questions.json`) with a simple question prompt structure.
+- Dataset here: https://huggingface.co/datasets/ergotts/ethics_questions
 - Each sample is mapped to a system prompt enforcing the `<reasoning>` / `<final_argument>` format, and a user prompt containing the question.
 - The model is trained to provide structured arguments and objections based on these questions