Update README.md

README.md

@@ -76,6 +76,62 @@ this model likes to speak poeticly and somtimes human like
 - Testing emergent personality in LLMs
 - Interactive storybots or surreal games
 
+### Exsample script
+
+
+~~~
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+def main():
+    model_name = "Notbobjoe/TalkT2-0.1b"
+    print(f"Loading model {model_name}...")
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+    model.eval()
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    model.to(device)
+    print("Model loaded. Start chatting! (type 'exit' to quit)")
+
+    chat_history = ""
+
+    while True:
+        user_input = input("You: ")
+        if user_input.lower() in ["exit", "quit"]:
+            print("Goodbye!")
+            break
+
+        # Add user input to chat history
+        chat_history += f"You: {user_input}\nTalkT2:"
+
+        # Tokenize input
+        prompt_tokens = tokenizer.encode(chat_history, return_tensors="pt").to(device)
+
+        # Generate response
+        output = model.generate(
+            prompt_tokens,
+            max_new_tokens=128,
+            do_sample=True,
+            temperature=0.4,
+            top_k=50,
+            top_p=0.95,
+            repetition_penalty=1.1,
+            pad_token_id=tokenizer.eos_token_id,
+            truncation=True
+        )
+
+        # Decode only newly generated tokens (skip prompt length)
+        generated_text = tokenizer.decode(output[0][prompt_tokens.shape[-1]:], skip_special_tokens=True)
+
+        print(f"TalkT2: {generated_text.strip()}")
+
+        # Append model reply to chat history
+        chat_history += generated_text + "\n"
+
+if __name__ == "__main__":
+    main()
+~~~
+
 ## ⚠️ Limitations
 - May contradict itself (e.g. “I’m human” → “I’m AI” → “No”)
 - Tends to get cryptic in longer conversations