LocalLLaMA

3 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago

MODERATORS

communick@poweruser.forum

Starling-RM-7B-alpha: New RLAIF Finetuned 7b Model beats Openchat 3.5 and comes close to GPT-4 (alien.top)

submitted 11 months ago by Legcor@alien.top to c/localllama@poweruser.forum

49 comments fedilink hide all child comments

https://preview.redd.it/3krgd1sg2z2c1.png?width=800&format=png&auto=webp&s=b76c5fb9fa22938c74ec3095f63adaec8ff2219d

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

you are viewing a single comment's thread
view the rest of the comments

[–] Evening_Ad6637@alien.top 1 points 11 months ago (1 children)

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.

[–] Competitive_Ad_5515@alien.top 1 points 11 months ago

Sure, but name-dropping the biggest name in the game and comparing yourself favourably to it is a big swing. It's either a naive at best marketing claim or it's untrue.