Add pipeline tag and improve model card

This PR adds the `pipeline_tag: text-generation` metadata, making the model discoverable via the Hub's filter and search functionalities. It also adds a more descriptive title to the model card, clarifies the AlpacaEval results section, and provides a link to the code.

README.md

@@ -1,19 +1,17 @@
 ---
-library_name: transformers
-license: mit
 datasets:
 - HuggingFaceH4/ultrafeedback_binarized
 language:
 - en
+library_name: transformers
+license: mit
+pipeline_tag: text-generation
 ---
 
-<!-- This is a model released from the preprint: *[Bootstrapping Language Models with DPO Implicit Rewards](https://arxiv.org/abs/2406.09760)*. Please refer to our [repository](https://github.com/sail-sg/dice) for more details. -->
-
 # Llama-3-Base-8B-DICE-Iter1
 
 This model was developed using [Bootstrapping Language Models with DPO Implicit Rewards](https://arxiv.org/abs/2406.09760) (DICE) at iteration 1, based on the [princeton-nlp/Llama-3-Base-8B-SFT-DPO](https://huggingface.co/princeton-nlp/Llama-3-Base-8B-SFT-DPO) architecture as the starting point. 
 
-<!-- We utilized the prompt sets extracted from [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized). -->
 
 ## Links to Other Models
 - [Llama-3-Base-8B-DICE-Iter1](https://huggingface.co/sail/Llama-3-Base-8B-DICE-Iter1)
@@ -26,7 +24,9 @@ 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](https://tatsu-lab.github.io/alpaca_eval/)
+## AlpacaEval Leaderboard Evaluation Results
+
+The following table shows the AlpacaEval leaderboard evaluation results for this model and related models:
 
 |                Model                           | LC. Win Rate | Win Rate | 
 |-------------------------------------------|:------------:|:--------:|
@@ -34,6 +34,8 @@ This model was developed using [Bootstrapping Language Models with DPO Implicit
 |[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)**
+
 ## Citation
 
 ```bibtex
@@ -43,4 +45,6 @@ This model was developed using [Bootstrapping Language Models with DPO Implicit
   journal={arXiv preprint arXiv:2406.09760},
   year={2024}
 }
-```
+```
+
+Code: https://github.com/sail-sg/dice