alt Hacker NewsI got a decent response with the same prompt
But yes, this will happen. 1.7B is already a tiny model, running that at 1-bit is going to lead to some behavioral issues and will need tuning of temperature/topP/repeatPenalty/etc, and probably a software fallback that detects pathological cases like this and simply retries. Just like we all had to do in the times of GPT 2 and GPT 3
I confirm I got an extremely detailed and long response for "Describe the process of pasteurization." with 1.7B. I had to tune nothing.