Update README.md

README.md

@@ -47,15 +47,23 @@ base_model: persadian/persadian-Nano-V4
 | Inference Efficiency   | Infrastructure-heavy            | ✅Optimized for constrained hardware          |
 | Innovation Focus       | Scale-first                     | ✅Efficiency-first with adaptive systems      |
 
-## Quick Start
-```from transformers import AutoModelForCausalLM, AutoTokenizer
+## Usage
 
-# The trust_remote_code=True flag is still required for custom models
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the custom model with its tokenizer
 model = AutoModelForCausalLM.from_pretrained(
     "persadian/persadian-nano-v4",
     trust_remote_code=True
 )
 tokenizer = AutoTokenizer.from_pretrained("persadian/persadian-nano-v4")
+
+# Generate text
+prompt = "Once upon a time"
+inputs = tokenizer(prompt, return_tensors="pt")
+output = model.generate(**inputs, max_new_tokens=50)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 
 ## Citation