Update README.md

README.md

@@ -67,4 +67,66 @@ If you ask it to perform a delivery (e.g., *"Fetch my laptop from the server roo
     {"type": "nav2", "cmd": "go_to_waypoint", "target": "john_desk"},
     {"type": "stunt", "cmd": "full_sit"}
   ]
-}
+}
+
+```
+## TEST SCRIPT
+```
+# ============================================================
+# ============================================================
+from unsloth import FastLanguageModel
+import torch
+
+MODEL_PATH = "./tasx_sft_merged"
+MAX_SEQ_LENGTH = 512
+
+print("⏳ Loading your fine-tuned TASX model...")
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = MODEL_PATH,
+    max_seq_length = MAX_SEQ_LENGTH,
+    dtype = torch.float16, 
+    load_in_4bit = False,  
+)
+
+FastLanguageModel.for_inference(model) 
+
+print("\n" + "="*50)
+print("TASX ROBOT COMMAND TESTER READY")
+print("Type a command in the box below and press Enter.")
+print("Type 'quit' or 'q' to stop.")
+print("="*50 + "\n")
+
+
+while True:
+    user_text = input("🎤 You: ")
+    
+    if user_text.lower() in ['quit', 'exit', 'q']:
+        print("Stopping inference. Great job!")
+        break
+        
+    if not user_text.strip():
+        continue
+
+   
+    prompt = f"<|im_start|>user\n{user_text}<|im_end|>\n<|im_start|>assistant\n"
+    
+    
+    inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
+
+    # Generate the output
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=150,
+        use_cache=True,
+        temperature=0.1,    
+        do_sample=True,
+    )
+
+    # Decode the output (slice off the prompt so we only see the assistant's new text)
+    response = tokenizer.batch_decode(
+        outputs[:, inputs.input_ids.shape[1]:], 
+        skip_special_tokens=True
+    )[0]
+    
+    print(f"TASX: {response.strip()}\n")
+```