公开(公告)号：US20240095463A1

公开(公告)日：2024-03-21

申请号：US17947946

申请日：2022-09-19

Applicant: Nvidia Corporation

Inventor： Ryan Leary ,  Jonathan Cohen

IPC: G06F40/40 ,  G06F40/284

CPC classification number: G06F40/40 ,  G06F40/284

Abstract: Approaches presented herein can provide for the performance of specific types of tasks using a large model, without a need to retrain the model. Custom endpoints can be trained for specific types of tasks, as may be indicated by the specification of one or more guidance mechanisms. A guidance mechanism can be added to or used along with a request to guide the model in performing a type of task with respect to a string of text. An endpoint receiving such a request can perform any marshalling needed to get the request in a format required by the model, and can add the guidance mechanisms to the request by, for example, prepending one or more text strings (or text prefixes) to a text-formatted request. A model receiving this string can process the text according to the guidance mechanisms. Such an approach can allow for a variety of tasks to be performed by a single model.

公开(公告)号：US20230342670A1

公开(公告)日：2023-10-26

申请号：US17727332

申请日：2022-04-22

Applicant: Nvidia Corporation

Inventor： Ryan Leary ,  Jonathan Cohen

IPC: G06N20/20 ,  G06F16/953 ,  G06F16/906

CPC classification number: G06N20/20 ,  G06F16/953 ,  G06F16/906

Abstract: Systems and methods provide a pipeline to develop and deploy machine learning models by using query/response pairs from a different machine learning model as training data. A set of model parameters are established and a trained machine learning models provides responses to input queries to develop query/response pairs. These query/response pairs may be used to train a different machine learning model. That model can be tested against the original model to determine whether they are in agreement, and when the models are in agreement the different machine learning model can be deployed as the primary model for the system.

公开(公告)号：US20230316000A1

公开(公告)日：2023-10-05

申请号：US17713470

申请日：2022-04-05

Applicant: Nvidia Corporation

Inventor： Purnendu Mukherjee ,  Vlad Getselevich ,  Ryan Leary

IPC: G06F40/35 ,  G06F40/56 ,  G06N3/04

CPC classification number: G06F40/35 ,  G06N3/0454 ,  G06F40/56

Abstract: Systems and methods determine an answer to an input query and provide a conversational response. The answer may be determined using a trained first neural network to extract the answer from a corpus of information. The answer and the input query may be provided to a second trained neural network to generate a formulation of the input query combined with the answer in order to generate a conversational response.