gensai.aiHyperparameters are the settings chosen before training: learning rate, batch size, number of layers. They are not learned by the model but condition the quality of learning; tuning them is a matter of methodical experimentation.
In practice at Gensai
On the usage side, Gensai tunes inference hyperparameters (temperature, maximum length) to control model behaviour.
Going beyond the definition?
From concept to project: Gensai builds custom, sovereign, GDPR-compliant AI solutions.
55 boulevard de Strasbourg, 75010 Paris