Fix import in README.md

For the example given, torch needs to be imported

README.md

@@ -24,6 +24,7 @@ datasets:
 Get started chatting with `StableLM-Tuned-Alpha` by using the following code snippet:
 
 ```python
+import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList
 
 tokenizer = AutoTokenizer.from_pretrained("StabilityAI/stablelm-tuned-alpha-7b")