VE-FORBRYDERNE/mtj-softtuner

Create soft prompts for fairseq 13B dense, GPT-J-6B and GPT-Neo-2.7B for free in a Google Colab TPU instance

42
/ 100
Emerging

This tool helps AI practitioners customize the behavior of large language models like GPT-J-6B or GPT-Neo-2.7B without needing to retrain the entire model. You provide a dataset relevant to your specific task, and it generates 'soft prompts' which are small, efficient additions that guide the model's output. This is ideal for AI developers or researchers who want to fine-tune existing large models for specialized text generation tasks.

No commits in the last 6 months.

Use this if you need to quickly adapt a large, pre-trained language model to a specific text generation style or domain using a small amount of your own data, without incurring the high cost of full model fine-tuning.

Not ideal if you are looking for a no-code solution for direct use by non-technical content creators, or if you need to drastically alter the model's fundamental understanding rather than just its output style.

AI-model-customization natural-language-generation text-prompt-engineering machine-learning-research language-model-fine-tuning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

28

Forks

20

Language

Python

License

Apache-2.0

Last pushed

Mar 01, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/VE-FORBRYDERNE/mtj-softtuner"

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