Update README.md

README.md

@@ -19,7 +19,7 @@ This modelcard aims to be a base template for new models. It has been generated
 
 ### Model Description
 
-The Digital Navigator model is designed to assist users by generating natural language responses to input queries. It is a fine-tuned GPT-2 model, customized for providing  assistanse to visitors of my university's website: https://cdm.uowm.gr/en/index/.
+The Digital Navigator model is designed to assist users by generating natural language responses to input queries. It is a fine-tuned GPT-2 model, customized for providing assistanse to the visitors of Communication and Digital Media Department's website: https://cdm.uowm.gr/en/index/.
 
 - **Developed by:** Papagiannakis Panagiotis
 - **Model type:** GPT-2 (Generative Pre-trained Transformer 2)
@@ -31,11 +31,7 @@ The Digital Navigator model is designed to assist users by generating natural la
 
 ### Direct Use
 
-The Digital Navigator model can be directly used for generating conversational responses in English. It is intended for use in chatbots, virtual assistants, and other applications requiring natural language understanding and generation.
-
-1. Conversational AI
-2. Customer Support
-3. Virtual Assistance
+Users do not have much of a choice but only use it for experimental and educational purposes, since the model was fine-tuned for specific answers and question related to the Department of Communication and Digital Media website: https://cdm.uowm.gr/en/index/.  
 
 ### Out-of-Scope Use
 
@@ -77,20 +73,9 @@ The model was trained using standard procedures for fine-tuning GPT-2 models.
 - Block Size: 128
 
 
-## Evaluation
-
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
 #### Metrics
 
-The model was evaluated using metrics like BLEU score for language quality, accuracy for factual correctness,
+The model was evaluated using metrics like BLEU score for language quality, accuracy for factual correctness, precision for the accuracy of positive predictions, recall for the ability to find all relevant instances, and F1 score to balance precision and recall.
 
 ### Results
 
@@ -110,7 +95,7 @@ Due to the high complexity and small variety of the data:
 ## Model Examination 
 
 
-- **Hardware Type:** [More Information Needed]
+- **Hardware Type:** NVIDIA T4
 - **Hours used:** 18 minutes and 47 seconds
 - **Cloud Provider:** Google Collab