Compact: 1 to 10 billion
Phi, Gemma, Llama 3 8B, Mistral 7B and most on-device and edge models. 82 models.
馃嚭馃嚫 United StatesStanford Alpaca
A cheap instruction-tuned LLaMA 7B built at Stanford in 2023Research 路 Research only 路 2023
馃嚞馃嚙 United KingdomGato
A single transformer network trained to do many tasks, from chat to robot controlMultimodal 路 Research only 路 2022
World1.58-bit large language model
A model whose weights hold only three values: -1, 0 and +1.Research 路 Open weights 路 2024