Update README.md

README.md

@@ -15,6 +15,16 @@ This repo contains a GGUF Quantized versions of the SFR-Iterative-DPO-Llama-3-8B
 weights from:
 [maldv/SFR-Iterative-DPO-LLaMA-3-8B-R](https://huggingface.co/maldv/SFR-Iterative-DPO-LLaMA-3-8B-R)
 
+## Prompt format
+
+```
+<|start_header_id|>system<|end_header_id|>
+{system_prompt}<|eot_id|>
+<|start_header_id|>user<|end_header_id|>
+{prompt}<|eot_id|>
+<|start_header_id|>assistant<|end_header_id|>
+
+
 ## Introduction
 We release a state-of-the-art instruct model of its class, **SFR-Iterative-DPO-LLaMA-3-8B-R**.
 On all three widely-used instruct model benchmarks: **Alpaca-Eval-V2**, **MT-Bench**, **Chat-Arena-Hard**, our model outperforms all models of similar size (e.g., LLaMA-3-8B-it), most large open-sourced models (e.g., Mixtral-8x7B-it),