Update README.md

README.md

@@ -86,6 +86,13 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 ### Inference on a small GPU (Consumer Hardware/Free Colab)
 
+The code is pretty much the same as above, but with a slight diferrence. 
+
+* Make sure `bitsandbytes` is installed correctly.
+* Your model loading must be `model = AutoModelForCausalLM.from_pretrained(model_name_or_id, load_in_8bit=True, torch_dtype=torch.float16, device_map="auto")`
+
+On _free version_ of Google Colab, you may face RAM problems. I guess using `low_cpu_mem_usage=True` in model loading would help. 
+
 ## Known Issues
 
 ## Special Thanks