Update README.md

README.md

@@ -6,7 +6,9 @@ language:
 - en
 ---
 the only files needed for inference is inference.py, word2idk.pkl, and lstm_Hxxx.safetensors
->python inference.py --temp 0.5 --top_k 64 --model_file lstm_H256.safetensors --start_sequence "User : what is the capital of France ? Bot :" --max_length 32
+
+input tokens mist be space separated, as they aren't tokenized like the training data is.
+>python inference.py --temp 0.5 --top_k 64 --model_file lstm_H256.safetensors --start_sequence "User : what is the capital of France ? Bot : " --max_length 32
 
 usually results in something like