Skip to content

Huggingface: Instruction Tuning Seq2Seq Models #2365

Open
@kevinscaria

Description

@kevinscaria

Problem Description
This notebook demonstrates how to instruction tune SeqSeq models using huggingface transformers. Instruction tuning is a machine learning paradigm where a model is trained to follow instructions for a given task. Instructions facilitate large language models (LLMs) with in-context learning to improve performance.

Metadata

Metadata

Assignees

Labels

enhancementNew feature or request

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions