SakanaAI/text-to-lora

Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

44
/ 100
Emerging

This project allows developers to quickly adapt large language models (LLMs) for specific tasks using only a text description of the task. You provide a plain language description of what the model should do, and it generates a specialized 'LoRA' adapter that customizes the LLM. This is ideal for machine learning engineers or researchers who need to fine-tune LLMs for various benchmarks or specialized applications without extensive data preparation.

1,214 stars. No commits in the last 6 months.

Use this if you need to rapidly customize a large language model's behavior for a new task using only a text description, without needing to gather and label large datasets for traditional fine-tuning.

Not ideal if you require absolute deterministic reproducibility for evaluations, as the underlying library for applying LoRA can introduce small variances.

LLM fine-tuning natural-language-processing model-adaptation AI-research prompt-engineering
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 17 / 25

How are scores calculated?

Stars

1,214

Forks

86

Language

Python

License

Apache-2.0

Category

llm-fine-tuning

Last pushed

Jun 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/SakanaAI/text-to-lora"

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