update about

src/about.py

@@ -43,41 +43,25 @@ points, spanning seven domains, 10 frequencies, multivariate inputs, and predict
 # Which evaluations are you running? how can people reproduce what you have?
 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:
+To participate in the GIFT-Eval leaderboard, follow these steps to evaluate your Time Series Model:
+
+Clone the Repository: Start by cloning the GIFT-Eval GitHub repository to your local machine using the following command:
 
 ```bash
-git clone https://github.com/SalesforceAIResearch/SFR-RAG
+git clone https://github.com/SalesforceAIResearch/gift-eval
 ```
 
 Navigate to the Directory: Move into the cloned repository's directory:
 
 
-``bash
-cd ContextualBench
-```
-
-Install Dependencies: Install all necessary dependencies by executing:
-
 ```bash
-pip install -r requirements.txt
+cd gift-eval
 ```
 
-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
-python run.py [dataset_name]
-```
+Follow the instruction in the README.md file to install the required dependencies, set up your environment and obtain the evaluation results. 
 
-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.
 """
 
 EVALUATION_QUEUE_TEXT = """