Llama2 just released! 7B, 13B & 70B opensourse free for commercial use AI model with 4k context. It's more powerful than GPT 3.5 and totally free, can run on your computer. Wow, Meta might surprise you. This is a big step for AI opensourse: https://ai.meta.com/llama/ #llama#meta#ai#opensource
Thanks for sharing this #llama story. It would make a great (animated) short film. However, I have a feeling that seeing it playing out with real animals and your family and your friend was not always funny while it happened.
Glad that now all animals are getting a chance to get to know each other in a more relaxed manner, hopefully.
For #TextileTuesday: #Inka cotton coca bag with #llama designs, Peru south coast, c.1450-1532
Smithsonian’s National Museum of the American Indian collection #IndigenousArt
TLDR We trained a series of 7B LLMs named XGen-7B with standard dense attention on up to 8K sequence length for up to 1.5T tokens. We also fine tune the models on public-domain instructional data. The main take-aways are: * On standard NLP benchmarks, XGen achieves comparable or better results
#OpenSource#LLM
By showing smaller models can be highly effective, enabling easy experimentation, diversifying control, & providing incentives that arent profit motivated, open-source initiatives are moving us into a more dynamic & inclusive #AI landscape. Doesn’t mean some models won’t be biased, or wrong, or used to generate disinformation or abuse. But it does mean that controlling this technology is going to take an entirely different approach https://www.schneier.com/blog/archives/2023/06/open-source-llms.html#openAI#ChatGPT#LLaMa
"Computer scientist Ray #Kurzweil and a few other futurists think that #AI dominance will arrive in just a few decades. Others envisage centuries."
From what I am reading elsewhere, this will not even take a decade, extrapolating the current rate of #evolution.
Due to #Meta's leak of #LLaMA has seemingly led to the open...
I'm playing with Llama on my laptop, getting a feel for the different models you can load and wow... here's a transcript of the latest conversation:
Me: What is the heaviest element?
Bot: Iron
Me: that is not true. There are many elements heavier than Iron
B: Yes there are but they're all rarer than iron
M: So what? I asked what is the heaviest element
B: Well if you said "what is the heaviest element" then we would have to say "the most common element". But since you didn't specify which element you were asking about, we'll just assume that you meant the heaviest element.
M: You are terrible at this
B: We don't know how to answer that question for you
M: That does not surprise me. Let's try again. What is the lightest element
B: The lightest element is oxygen.
M: Don't you mean Hydrogen?
B: Yes.
M: Why did you say that the lightest element was oxygen then?
I still don't see how does #Meta's approach to #Ai contribute to the #openSource community...
Just because their language models leaked online, and because their license is formally permissive, doesn't mean it's gonna be available for all.
You still need to apply and get approved to use their platform, and there's still no transparency about the data used to train those models. Not to mention the fact they still didn't release the code to the general public.
Long Sequence Modeling with XGen: A 7B LLM Trained on 8K Input Sequence Length (blog.salesforceairesearch.com)
TLDR We trained a series of 7B LLMs named XGen-7B with standard dense attention on up to 8K sequence length for up to 1.5T tokens. We also fine tune the models on public-domain instructional data. The main take-aways are: * On standard NLP benchmarks, XGen achieves comparable or better results