I came across this new finetuned model based on Openchat 3.5 which is apparently trained used Reinforcement Learning from AI Feedback (RLAIF).
https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
Check out this tweet: https://twitter.com/bindureddy/status/1729253715549602071
I’ve seen the “… beats GPT-4” enough times that now whenever I see a title that suggests a tiny model can compete with GPT-4 I see it as a negative signal; that the authors are bullshitting through some benchmarks or some other shenanigans.
It’s annoying because the models might be legitimately good models for being open and within their weight class but now you’ve put my brain in BS detecting mode and I can’t trust you’ve done good faith measurement anymore.
Yeah I dont think authors are intentionally bullshitting or intentionally doing “benchmark cosmetics”, but maybe it’s more lack of knowledge on whats going on in terms of (most of) benchmarks and their the image that has become ruined in the meantime.
There are SO many models “bullshitting through some benchmarks or some other shenanigans” that I’m cooking my own benchmark system LOL.