Stephen Bach, assistant professor at Brown University, explains the three phases of training a large language model (LLM) and how each impacts the final performance of the neural network.

This was excerpted from a longer talk Bach gave at Snorkel AI's January 2024 Enterprise LLM Summit.

See a full summary of Snorkel AI's Enterprise LLM Summit: Building GenAI with your Data here:
[ Ссылка ]

See his longer talk here: [ Ссылка ]

See more videos from Snorkel AI here: youtube.com/channel/UC6MQ2p8gZFYdTLEV8cysE6Q?sub_confirmation=1

See recordings of all of the day's sessions here: [ Ссылка ]
More related videos: [ Ссылка ]

#largelanguagemodels, #aitraining, #neuralnetworks

свернуть