Allow cancellation of prediction while running prompt

Open Assistant is great, but sometimes it will predict a long answer where I can spot a misinterpretation right away. Whether this is because my prompt was faulty and I realise this too late, or the model hallucinates. Either way, having to wait for the entire prediction to load significantly reduces the UX (due to waiting time). It would be useful to be able to abort the prediction.

Model OA_SFT_Llama_30B_6 
Top K 50 
Top P 0.95 
Temperature 0.9 
Repetition penalty 1.2 
Max new tokens 1024