Update README.md

README.md

@@ -44,41 +44,81 @@ This model is designed for **customer support automation in the telecom industry
 ## How to Get Started with the Model
 
 
+Here is the full **markdown-formatted content** for your **Hugging Face model card**:
+
+---
+
+```md
+# DeepSeek-R1-Telecom-Chatbot
+
+## Model Description
+
+This is a fine-tuned version of **DeepSeek-R1-Distill-Llama-8B**, optimized for **telecom-related queries**. The model has been fine-tuned to provide **concise and factual answers**, ensuring that it does **not role-play as a customer service agent**.
+
+- **Developed by**: Mohamed Abdulaziz  
+- **Funded by (optional)**: Self-funded  
+- **Model type**: Fine-tuned DeepSeek-R1-Distill-Llama-8B  
+- **License**: MIT License  
+
+---
+
+## 📌 How to Use the Model
+
+### **1️⃣ Import necessary libraries**
+```python
 import torch
 from unsloth import FastLanguageModel
 from transformers import AutoTokenizer
+```
 
-✅ Define model path (modify if using a different source)
+### **2️⃣ Define model path (Modify if using a different source)**
+```python
 model_path = "moo100/DeepSeek-R1-telecom-chatbot"
+```
 
-✅ Load model and tokenizer
+### **3️⃣ Load the model and tokenizer**
+```python
 model, tokenizer = FastLanguageModel.from_pretrained(
     model_path, 
     max_seq_length=1024,  # Ensures compatibility with training length
     dtype=None  # Uses default precision
 )
+```
 
-✅ Optimize model for **fast inference** with Unsloth
+### **4️⃣ Optimize model for fast inference with Unsloth**
+```python
 model = FastLanguageModel.for_inference(model)
+```
 
-✅ Move model to GPU if available, otherwise use CPU
+### **5️⃣ Move model to GPU if available, otherwise use CPU**
+```python
 device = "cuda" if torch.cuda.is_available() else "cpu"
 model.to(device)
+```
 
-✅ Define system instruction to guide responses
-system_instruction = """You are an AI assistant. Answer user questions concisely and factually.
+### **6️⃣ Define system instruction to guide model responses**
+```python
+system_instruction = """You are an AI assistant. Answer user questions concisely and factually. 
 Do NOT role-play as a customer service agent. Only answer the user's query."""
+```
 
-✅ Define user input (replace with any query)
+### **7️⃣ Define user input (Replace with any query)**
+```python
 user_input = "What are the benefits of 5G?"
+```
 
-✅ Construct full prompt with instructions and user query
+### **8️⃣ Construct full prompt with instructions and user query**
+```python
 full_prompt = f"{system_instruction}\n\nUser: {user_input}\nAssistant:"
+```
 
-✅ Tokenize input prompt
+### **9️⃣ Tokenize input prompt**
+```python
 inputs = tokenizer(full_prompt, return_tensors="pt").to(device)
+```
 
-✅ Generate model response with controlled stopping criteria
+### **🔟 Generate model response with controlled stopping criteria**
+```python
 outputs = model.generate(
     input_ids=inputs.input_ids,  # Encoded input tokens
     attention_mask=inputs.attention_mask,  # Mask for input length
@@ -88,12 +128,17 @@ outputs = model.generate(
     top_k=50,  # Samples from top 50 probable words
     eos_token_id=tokenizer.eos_token_id,  # Stops at end-of-sentence token
 )
+```
 
-✅ Decode and extract only the newly generated response
+### **1️⃣1️⃣ Decode and extract only the newly generated response**
+```python
 response = tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True)
+```
 
-✅ Print the AI-generated response
-print(response.strip())  
+### **1️⃣2️⃣ Print the AI-generated response**
+```python
+print(response.strip())
+```
 
 
 
@@ -116,3 +161,24 @@ talkmap/telecom-conversation-corpus
 
   Below are the training metrics recorded during fine-tuning:
   https://drive.google.com/file/d/1-SOfG8K3Qt2WSEuyj3kFhGYOYMB5Gk2r/view?usp=sharing
+
+
+# Evaluation
+
+## Methodology
+
+The chatbot was evaluated using Meta-Llama-3.3-70B-Instruct, assessing relevance, correctness, and fluency of its responses.
+
+## Results
+
+Meta-Llama-3.3-70B-Instruct Evaluation:
+
+Relevance: 9/10
+The response is highly relevant to the user’s query about 5G benefits, providing a concise and informative summary.
+
+Correctness: 10/10
+The response is factually accurate, highlighting key advantages such as faster data speeds, lower latency, increased capacity, and broader device compatibility.
+
+Fluency: 9/10
+The response is well-structured, grammatically sound, and easy to understand. Minor refinements could further enhance readability.
+