Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Meta Llama 3

llama.meta.com

Post reply on HN
Print view View original

11–20 of 965 posts

Re: Meta Llama 3

#11

Post by trevor-e »

namanyayg wrote: post #7

I'm so surprised that Meta is actually leading the open source AI landscape?! I've used llama2 extensively and can't wait to try out llama3 now. I can't believe that it does better than Claude 3 in benchmarks (though admittedly claude 3 seems to have been nerfed recently) I sure do wish there was more info about how its trained and its training data.

Why do people keep saying that Claude3 has been nerfed? Their CTO has said on Twitter multiple times that not a single byte has been changed since its launch, so I'm curious why I keep hearing this.

edit: having trouble finding the tweet I saw recently, it might have been from their lead engineer and not the CTO.

Re: Meta Llama 3

#12

Post by oersted »

namanyayg wrote: post #7

I'm so surprised that Meta is actually leading the open source AI landscape?! I've used llama2 extensively and can't wait to try out llama3 now. I can't believe that it does better than Claude 3 in benchmarks (though admittedly claude 3 seems to have been nerfed recently) I sure do wish there was more info about how its trained and its training data.

Better than Claude 3 Sonnet but Claude 3 Opus is significantly more powerful, albeit I'm not sure how they compare accounting for parameter size.

Re: Meta Llama 3

#14

Post by Anuiran »

Awesome, but I am surprised by the constrained context window as it balloons everywhere else.

Am I missing something? 8k seems quite low in current landscape.

Re: Meta Llama 3

#15

Post by CuriouslyC »

jelled wrote: post #3

Looks like 8K context length. Seems to compare well against Gemini Pro 1.5 and Claude 3 Sonnet according to the included benchmarks.

If it's limited to 8k context length then it's not competing with sonnet at all IMO. Sonnet has a 200k context length and it's decent at pulling stuff from it, with just an 8k context length this model won't be great for RAG applications, instead it'll be used for chat and transforming data from one type to another.

Re: Meta Llama 3

#17

Post by nickthegreek »

bbig wrote: post #4

They've got a console for it as well, https://www.meta.ai/ And announcing a lot of integration across the Meta product suite, https://about.fb.com/news/2024/04/meta-ai-assistant-built-wi... Neglected to include comparisons against GPT-4-Turbo or Claude Opus, so I guess it's far from being a frontier model. We'll see how it fares in the LLM Arena.

And they even allow you to use it without logging in. Didnt expect that from Meta.

Re: Meta Llama 3

#19

Post by oersted »

minimaxir wrote: post #5

The model card has the benchmark results relative to other Llama models including Llama 2: https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md... The dramatic performance increase of Llama 3 relative to Llama 2 (even Llama 2 13B!) is very impressive. Doubling the context window to 8k will open a lot of new oppertunities too.

For the instruction tuned models, Llama 3 8B is even significantly better than Llama 2 70B!
Post reply on HN