Make the README consistent for the model over iterations

README.md

@@ -24,9 +24,7 @@ This model was developed using [Bootstrapping Language Models with DPO Implicit
 - License: MIT
 - Fine-tuned from model: princeton-nlp/Llama-3-Base-8B-SFT-DPO
 
-## AlpacaEval Leaderboard Evaluation Results
-
-The following table shows the AlpacaEval leaderboard evaluation results for this model and related models:
+## [AlpacaEval Leaderboard Evaluation Results](https://tatsu-lab.github.io/alpaca_eval/)
 
 |                Model                           | LC. Win Rate | Win Rate | 
 |-------------------------------------------|:------------:|:--------:|
@@ -34,7 +32,8 @@ The following table shows the AlpacaEval leaderboard evaluation results for this
 |[Llama-3-Base-8B-DICE-Iter1](https://huggingface.co/sail/Llama-3-Base-8B-DICE-Iter1) |25.08 |25.77
 |[Llama-3-Base-8B-DICE-Iter2](https://huggingface.co/sail/Llama-3-Base-8B-DICE-Iter2) |**27.55** |**30.99**
 
-**(LC = Length Controlled, WR = Win Rate)**
+## Code
+https://github.com/sail-sg/dice
 
 ## Citation
 
@@ -45,6 +44,4 @@ The following table shows the AlpacaEval leaderboard evaluation results for this
   journal={arXiv preprint arXiv:2406.09760},
   year={2024}
 }
-```
-
-Code: https://github.com/sail-sg/dice
+```