YaLM 100B is a GPT-like neural network for generating and processing text. It can be used freely by developers and researchers from all over the world.
The model leverages 100 billion parameters. It took 65 days to train the model on a cluster of 800 A100 graphics cards and 1.7 TB of online texts, books, and countless other sources in both English and Russian.
github.com
Calling all my AI / ML boys to the yard.
@Sartre @Cognitive @spectrejoe @Alma @mdevo @NulledCode @ghengis_khan
That GPU req tho!
The model leverages 100 billion parameters. It took 65 days to train the model on a cluster of 800 A100 graphics cards and 1.7 TB of online texts, books, and countless other sources in both English and Russian.
GitHub - yandex/YaLM-100B: Pretrained language model with 100B parameters
Pretrained language model with 100B parameters. Contribute to yandex/YaLM-100B development by creating an account on GitHub.
Calling all my AI / ML boys to the yard.
@Sartre @Cognitive @spectrejoe @Alma @mdevo @NulledCode @ghengis_khan
That GPU req tho!