Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
1–8 of 8 posts
Re: Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
#2Also pythia: https://www.pythia.org/
A high energy physics simulation library
Re: Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
#3Also pythia: https://www.pythia.org/ A high energy physics simulation library
I'm ok with this as long as it's not the n-th software project called Spark.
Re: Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
#4Also pythia: https://www.pythia.org/ A high energy physics simulation library
I asked ChatGPT what a top quark can decay into. Among other things it suggested a top quark could decay into a photon. ChatGPT seems not to have learned about baryon number conservation...
On a more serious note, Pythia has been around for 40 years... surely they could have picked a better name...
Re: Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
#5Is this the link?
https://engineering.fb.com/2019/05/21/ai-research/pythia/
or maybe this? https://github.com/EleutherAI/pythia
I'm confused.
Re: Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
#6Is this the link? https://engineering.fb.com/2019/05/21/ai-research/pythia/ or maybe this? https://github.com/EleutherAI/pythia I'm confused.
No, the title is linked. The title refers to Pythia by EleutherAI for evaluating LLMs.
You linked something that is a framework for multimodal models by facebook.
Re: Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
#7I've been happily using Pythia in Acronymy Assistant: https://github.com/dwrensha/acronymy-assistant
It's quite convenient to have a continuous range of model sizes. Usually I want "the largest model that fits on my GPU", but sometimes I want to trade between quality and performance, and Pythia makes that easy.
Re: Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
#8Also pythia: https://www.pythia.org/ A high energy physics simulation library
I asked ChatGPT what a top quark can decay into. Among other things it suggested a top quark could decay into a photon. ChatGPT seems not to have learned about baryon number conservation... On a more serious note, Pythia has been around for 40 years... surely they could have picked a better name...
I asked ChatGPT (GPT-4) model about the top quark decay channels and it was mostly correct about top decay to W and b quark. It then started listing possibilities of further W decays which were mostly correct.
On your same serious note, particle physicists are the worst in naming things, let's not forget that people came up with a very unique name of "ROOT".