Update README.md

README.md

@@ -10,27 +10,27 @@ datasets:
 metrics:
 - accuracy
 tags:
-- pair-ranker
-- pair_ranker
 - reward_model
 - reward-model
-- pairrm
-- pair-rm
 - RLHF
+- evaluation
+- llm
+- instruction
+- reranking
 language:
 - en
+pipeline_tag: text-generation
 ---
 
-Inspired by [DeBERTa Reward Model Series](https://huggingface.co/OpenAssistant/reward-model-deberta-v3-large-v2) 
-`llm-blender/PairRM` is pairranker version finetuned specifically as a reward model using deberta-v3-large. 
 
 - Github: [https://github.com/yuchenlin/LLM-Blender](https://github.com/yuchenlin/LLM-Blender)
 - Paper: [https://arxiv.org/abs/2306.02561](https://arxiv.org/abs/2306.02561)
 - Space Demo: [https://huggingface.co/spaces/llm-blender/LLM-Blender](https://huggingface.co/spaces/llm-blender/LLM-Blender)
 
-## Usage Example
+## Introduction 
 
-### Installation
+
+## Installation
 Since PairRanker contains some custom layers and tokens. We recommend use PairRM with our llm-blender code API.
 - First install `llm-blender`
 ```bash
@@ -44,6 +44,9 @@ blender = llm_blender.Blender()
 blender.loadranker("llm-blender/PairRM") # load PairRM
 ```
 
+
+## Usage 
+
 ### Use case 1: Compare responses (Quality Evaluator)
 
 - Then you can rank candidate responses with the following function
@@ -198,7 +201,9 @@ Two reasons to attribute:
 
 
 
-## Citation
+
+
+## Citation & Credits 
 If you are using PairRM in your research, please cite LLM-blender.
 ```bibtex
 @inproceedings{llm-blender-2023,
@@ -209,3 +214,5 @@ If you are using PairRM in your research, please cite LLM-blender.
 }
 
 ```
+
+