Update README.md

README.md

@@ -24,14 +24,14 @@ It’s designed to serve as an intelligent coding copilot: generate code, explai
 
 ## 🚀 Features
 
-- 🔍 **Multi-task formatting**: Instruction-tuned samples with tasks like code generation, docstring generation, function completion, and code improvement.
-- ⚡ **Efficient LoRA training** using `PEFT` and `transformers`.
-- 🧠 Token-level preprocessing with Hugging Face's tokenizer and trainer utilities.
-- 📊 Training tracked via Weights & Biases (W&B).
-- 🔬 Dataset sampling + tokenization to stay memory-efficient.
-- 🛠️ Ready for inference integration and API deployment.
+-  **Multi-task formatting**: Instruction-tuned samples with tasks like code generation, docstring generation, function completion, and code improvement.
+-  **Efficient LoRA training** using `PEFT` and `transformers`.
+-  Token-level preprocessing with Hugging Face's tokenizer and trainer utilities.
+   Training tracked via Weights & Biases (W&B).
+-  Dataset sampling + tokenization to stay memory-efficient.
+-  Ready for inference integration and API deployment.
 
-  ## 🧪 Dataset
+  ## Dataset
 
 - **Source**: `code_search_net` (Python split)
 - **Fields Used**: `func_code_string`, `func_documentation_string`
@@ -40,7 +40,7 @@ It’s designed to serve as an intelligent coding copilot: generate code, explai
   - Validation: 200 samples
   - Test: 200 samples
 
-## 🧪 Format: Multi-Task Examples
+##  Format: Multi-Task Examples
 
 Examples were formatted into prompts like:
 
@@ -52,7 +52,7 @@ Response:
 def factorial(n):
 return 1 if n == 0 else n * factorial(n - 1)
 
-## 🧠 Model
+##  Model
 
 - **Base**: `bigcode/starcoder2-3b`
 - **PEFT Config**:
@@ -67,7 +67,7 @@ return 1 if n == 0 else n * factorial(n - 1)
   - `save_steps=100`
   - `logging_dir=./logs`
 
-## 🧰 Dependencies
+##  Dependencies
 
 ```bash
 pip install transformers peft datasets accelerate wandb