g1: Using Llama-3.1 70B on Groq to create o1-like reasoning chains

Re:g1: Using Llama-3.1 70B on Groq to create o1-like reasoni... by quantadev on Monday September 16, 2024 @02:17PM (#41558888)

I recommend getting on Twitter to follow closely the leading individuals in the field of AI, and also watch the leading Youtube channels dedicated to AI research.

[ Parent | on HN ]

Re:g1: Using Llama-3.1 70B on Groq to create o1-like reasoni... by whimsicalism on Monday September 16, 2024 @02:32PM (#41559044)

can you link to one speculating about multiple inferences for their CoT? i am curious

e: answer to my own question https://x.com/_xjdr/status/1835352391648158189

[ Parent | on HN ]

Re:g1: Using Llama-3.1 70B on Groq to create o1-like reasoni... by quantadev on Monday September 16, 2024 @02:56PM (#41559291)

So far it's been unanimous. Everyone I've heard talk about it believes Strawberry is mainly just CoT. I'm not saying they didn't fine tune a model too, I'm just saying I agree with most people that clever CoT is where most of the leap in capability seems to have come from.

[ Parent | on HN ]

Re:g1: Using Llama-3.1 70B on Groq to create o1-like reasoni... by whimsicalism on Monday September 16, 2024 @03:36PM (#41559750)

> believes Strawberry is mainly just CoT. I'm not saying they didn't fine tune a model too

You don't see the scaling with respect to token length with non-FT'd CoT like this, in my opinion.

[ Parent | on HN ]

Re:g1: Using Llama-3.1 70B on Groq to create o1-like reasoni... by quantadev on Monday September 16, 2024 @04:03PM (#41560102)

I haven't even added Strawberry support to my app yet, and so haven't checked what it's context length is, but you're right that additional context length is a scaling factor that's totally independent of whether CoT is used or not.

I'm just saying whatever hey did in their model, I think they also added CoT on top of it all, as the outer layer of the onion so to speak.

[ Parent | on HN ]