arrmansa/Basic-UI-for-GPT-J-6B-with-low-vram

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.

38
/ 100
Emerging

This project helps developers run a large language model (GPT-J-6B) on computers with limited graphics card memory. It takes the model and user input, then processes it using a combination of RAM and VRAM to generate text outputs. This is designed for AI/ML developers or researchers who need to experiment with large models on less powerful hardware.

113 stars. No commits in the last 6 months.

Use this if you are a developer working with large language models and your machine has limited VRAM (e.g., 4-8 GB) but sufficient RAM to load the model.

Not ideal if you have ample VRAM (12GB+) or are not a developer looking to run specific large language models locally.

AI-development large-language-models resource-constrained-ML local-model-deployment ML-experimentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

113

Forks

12

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Dec 23, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/arrmansa/Basic-UI-for-GPT-J-6B-with-low-vram"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.