4d ago

OLMo – a fully open LLM outperforming GPT 4o mini

OLMo is a family of fully open language models, enabling the discovery of new and innovative approaches to model pretraining.

2 comments

Fully open is extremely good, it uses entirely open datasets and has all training and inference code. We need more things like that.

Just checked this out on HF and this shit isn't even on the top 100 in any leaderboard. What gives?