Seonglae ChoGood for toy model with AI Scaling
important model memorization since the dataset are fully available and olmo-3.1 is same
- Pythia-14m
- Pythia-70m
- Pythia-160m
- Pythia-410m
- Pythia-1b
- Pythia-1.4b
- Pythia-2.8b
- Pythia-12b
Pythia Scaling Suite - a EleutherAI Collection
Pythia is the first LLM suite designed specifically to enable scientific research on LLMs. To learn more see https://github.com/EleutherAI/pythia
https://huggingface.co/collections/EleutherAI/pythia-scaling-suite-64fb5dfa8c21ebb3db7ad2e1
