Update src/about.py

src/about.py

@@ -43,37 +43,39 @@ LLM_BENCHMARKS_TEXT = f"""
 How It Works
 To participate in the ContextualBench leaderboard, follow these steps to evaluate your Large Language Model (LLM) using the ContextualBench framework:
 
-    Clone the Repository: Start by cloning the ContextualBench GitHub repository to your local machine using the following command:
-
-    bash
-    git clone https://github.com/ShreyPandit/ContextualBench
+Clone the Repository: Start by cloning the ContextualBench GitHub repository to your local machine using the following command:
 
+```bash
+git clone https://github.com/SalesforceAIResearch/SFR-RAG
+```
 
 Navigate to the Directory: Move into the cloned repository's directory:
 
 
-bash
+``bash
 cd ContextualBench
-
+```
 
 Install Dependencies: Install all necessary dependencies by executing:
 
-bash
+```bash
 pip install -r requirements.txt
+```
 
 Prepare Your Model and Dataset: Set up your model and dataset according to the guidelines provided in the repository's documentation.
 Run the Evaluation Script: Execute the evaluation script to generate outputs for your model on the specified dataset:
 
 
-bash
+```bash
 python run.py [dataset_name]
-
+```
     
 Collect and Format Outputs: Gather the outputs generated for each dataset and format them according to the leaderboard submission guidelines.
 Submit Your Results: Email the formatted outputs to the author's email address for evaluation. Our team will assess the performance and update the leaderboard accordingly.
 
 Reproducibility
-Ensuring reproducibility is a key aspect of the ContextualBench leaderboard. By following the standardized steps outlined above, participants can consistently reproduce evaluation results. This process not only facilitates fair comparisons across different models but also encourages transparency and reliability in model assessments. Participants are encouraged to adhere strictly to the submission guidelines to ensure their results are accurately reflected on the leaderboard.
+Ensuring reproducibility is a key aspect of the ContextualBench leaderboard. 
+By following the standardized steps outlined above, participants can consistently reproduce evaluation results. This process not only facilitates fair comparisons across different models but also encourages transparency and reliability in model assessments. Participants are encouraged to adhere strictly to the submission guidelines to ensure their results are accurately reflected on the leaderboard.
 """
 
 EVALUATION_QUEUE_TEXT = """
@@ -82,13 +84,11 @@ EVALUATION_QUEUE_TEXT = """
 
 CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
 CITATION_BUTTON_TEXT = r"""
-
 ```
 @article{nguyen2024sfrrag,
   title={SFR-RAG: Towards Contextually Faithful LLMs},
   author={Nguyen, Xuan-Phi and Pandit, Shrey and Purushwalkam, Senthil and Xu, Austin and Chen, Hailin and Ming, Yifei and Ke, Zixuan and Savarese, Silvio and Xong, Caiming and Joty, Shafiq},
   year={2024}
 }
-
 ```
 """