| |
|
| |
Real phone conversations. A small model. A frontier-model comparison.
See Phonely's approach to turning messy production data into a training set, fine-tuning on AWS GPUs, & evaluating whether the model actually gets better.
Registration
RSVP on this Luma page.
Complete your AWS Builder Center registration for venue entry.
Both steps are required. A Luma RSVP does not automatically register you with AWS or grant entry to the AWS Builder Loft. Everyone attending, including speakers & hosts, must register with AWS.
Event details
Join Will Bodewes & Amit Kiran Rege from Phonely for an evening of fine-tuning a small model to hold a conversation. We'll start with a set of real, scrubbed phone conversations, some of which contain bad responses, & train a small model to respond the way a person would.
We'll walk through Phonely's approach to cleaning the dataset, running the fine-tune on AWS GPUs, & building an eval that compares the base model, the fine-tuned model, & a stronger frontier model.
In the course of this event, you will learn how to turn messy production data into a training set, how to tell whether a fine-tuned model is actually better, & how to read its failures to decide what to change next.
Speakers
Will Bodewes, CEO, Phonely
Amit Kiran Rege, ML Researcher, Phonely
Who it's for
Engineers, ML & AI practitioners, & technical founders. Intermediate level.
Food & soft drinks provided.
Entry requirements
All guests must be 18+ & show a valid government-issued physical photo ID at check-in. Digital IDs are not accepted. Scooters & bikes are not permitted in Amazon buildings. No on-site parking is available.
|
|
|
|
|
|
|
|