Update README.md

README.md

@@ -6,14 +6,8 @@ model-index:
           type: text-generation
         dataset:
           name: rag_contents
-          type: custom
+          type: pricing_info
         metrics:
-          - name: Perplexity
-            type: perplexity
-            value: 20.75  # Example value, update with your actual score
-          - name: BLEU
-            type: bleu
-            value: 35.5  # Example value, update with your actual score
           - name: Retrieval Accuracy
             type: custom
             value: 85.0  # Example value, update with your actual score
@@ -25,36 +19,36 @@ model-index:
         metrics:
           - name: Pricing Retrieval Accuracy
             type: custom
-            value: 88.5  # Example value, update with your actual score
+            value: 75
     source:
       name: Cloud Cents
-      url: https://cloud-cents.vercel.app
+      url: https://huggingface.co/mattmajestic/cloud-llm
 ---
 
-# Cloud Service RAG Model
+# ☁️ Cloud Cents RAG Model ☁️
 
-## Model Description
-This model is a fine-tuned GPT-2 model designed to answer cloud-related questions about AWS, Azure, GCP, and other cloud platforms. It uses Retrieval-Augmented Generation (RAG) to combine document retrieval with text generation, leveraging cloud-related documents and real-time pricing information.
+## 📖 Model Description
+This model is a fine-tuned GPT-2 model designed to answer cloud-related questions about AWS, Azure, GCP, and other cloud platforms. It uses **Retrieval-Augmented Generation (RAG)** to combine document retrieval with text generation, leveraging cloud-related documents and real-time pricing information.
 
-## Intended Use
-- Cloud service comparisons (e.g., AWS vs Azure)
-- Real-time cloud pricing queries
-- General information about cloud platforms and services
+## 🛠 Intended Use
+- 🔍 Cloud service comparisons (e.g., AWS vs Azure)
+- 💰 Real-time cloud pricing queries
+- 🌐 General information about cloud platforms and services
 
-## Pipeline
+## 🔧 Pipeline
 `text-generation` with `retrieval-augmented generation (RAG)`
-- Document retrieval from `rag_contents` and `pricing_info`
-- Text generation using fine-tuned GPT-2
+- 📚 Document retrieval from `rag_contents` and `pricing_info`
+- ✍️ Text generation using fine-tuned GPT-2
 
-## Datasets
+## 📊 Datasets
 - **rag_contents**: Contains cloud-related documents from sources such as AWS, Azure, GCP.
 - **pricing_info**: Provides real-time pricing details for cloud services (e.g., EC2, Blob Storage, Container Registry).
 
-## Metrics
+## 📈 Metrics
 - **Perplexity**: Evaluated for fluency of text generation.
 - **BLEU**: Used for measuring the accuracy of generated answers.
 - **Retrieval Accuracy**: Custom metric for FAISS-based document retrieval.
 
-## Limitations
-- The model may not always retrieve the most up-to-date information about cloud services.
-- The retrieval and generation quality is based on the documents stored in the `rag_contents` table.
+## ⚠️ Limitations
+- 🕑 The model may not always retrieve the most up-to-date information about cloud services.
+- 📂 The retrieval and generation quality is based on the documents stored in the `rag_contents` table.