Update README.md

README.md

@@ -74,6 +74,7 @@ This setup preserved general reasoning ability while improving spatial accuracy.
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
 model = AutoModelForCausalLM.from_pretrained("sareena/spatial_lora_mistral")
 tokenizer = AutoTokenizer.from_pretrained("sareena/spatial_lora_mistral")
@@ -84,10 +85,19 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 ```
 
-
 # Prompt Format
+The model is trained on instruction-style input with a spatial reasoning question:
+
+```text
+Q: The couch is to the left of the table. The lamp is on the couch. Where is the lamp in relation to the table?
+```
 
 # Expected Output Format
+The output is a short, natural language spatial answer:
+
+```text
+A: left 
+```
 
 # Limitations