It works the other way too! People don't know that 3 or 2 bits can still be good because they've read the hivemind's opinion that <4bit is unusable trash and they've never experimented themselves. The reality is a lot more nuanced than that, especially for models as large as 284B.
alt Hacker News
It works the other way too! People don't know that 3 or 2 bits can still be good because they've read the hivemind's opinion that <4bit is unusable trash and they've never experimented themselves. The reality is a lot more nuanced than that, especially for models as large as 284B.