Thanks to visit codestin.com
Credit goes to github.com

Skip to content

[Feature request] Implement 8-bit GPT-J #5

New issue
New issue
Closed
#27
Closed
[Feature request] Implement 8-bit GPT-J#5
#27
Labels
enhancementNew feature or request
@pablogranolabar

Description

@pablogranolabar
pablogranolabar
opened on Nov 13, 2022

Results in ~11Gb weights vs. 16Gb, implemented in PyTorch now as load_in_8bit=True:

https://huggingface.co/hivemind/gpt-j-6B-8bit

Metadata

Metadata

Assignees

No one assigned

    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