Basic-UI-for-GPT-J-6B-with-low-vram icon indicating copy to clipboard operation
Basic-UI-for-GPT-J-6B-with-low-vram copied to clipboard

verified publisher icon arrmansa
→

Metadata

A repository to run gpt-j-6b on low vram machines (4.2 gb minimum vram for 2000 token context, 3.5 gb for 1000 token context). Model loading takes 12gb free ram.

Results 4 Basic-UI-for-GPT-J-6B-with-low-vram issues
Sort by recently updated
recently updated
newest added
trafficstars

The results are much worse than with original GPT-J-6B

11 comment

Even though memory savings are great, I hoped that the quality will be the same, but it is not. For example, on https://6b.eleuther.ai/ I try the following prompt (highlighted in...

Lissanro avatar Lissanro

Update README.md

Download

RichardScottOZ avatar RichardScottOZ

RuntimeError: where expected condition to be a boolean tensor, but got a tensor with dtype Float

I was successful in getting your code to work on my 2060 laptop after a few tweeks. I just got a tesla M40 card in and am looking at running...

ebolam avatar ebolam

Where to do the pip install? Can you please make a bit elaborate readme.md

1 comment

indianninja2018 avatar indianninja2018

← Metadata

114
Stars
12
Forks
Watchers

Owner

verified publisher icon arrmansa

Metadata

A repository to run gpt-j-6b on low vram machines (4.2 gb minimum vram for 2000 token context, 3.5 gb for 1000 token context). Model loading takes 12gb free ram.

Back