From Llama 3 to Deepseek R1 and beyond: a year of LLMs in retrospective

[admin]

The year 2023 was ripe in open-source LLMs, and the community managed to surpass the original ChatGPT model. The wave continued in 2024-2025, and the gap to the best closed-source models is now reduced to a few months. This talk will go over the major model architecture, training and inference changes that pushed the state-of-the-art in LLMs and VLMs over the last year.


The post From Llama 3 to Deepseek R1 and beyond: a year of LLMs in retrospective appeared first on Priberam.