gszfwsb/Data-Whisperer

Code for ACL 2025 Main paper "Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning".

26
/ 100
Experimental

This project helps machine learning engineers and researchers efficiently fine-tune large language models (LLMs) for specific tasks. It takes an initial dataset and an LLM as input, then identifies the most impactful data points to create a smaller, optimized dataset for training. This results in more efficient and potentially higher-performing task-specific LLMs.

No commits in the last 6 months.

Use this if you need to fine-tune an LLM for a specific application but want to avoid using your entire dataset to save time and computational resources.

Not ideal if you are not working with LLMs, or if you prefer to use your full dataset for fine-tuning without any data selection.

LLM fine-tuning data efficiency natural language processing model training AI research
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 7 / 25
Community 9 / 25

How are scores calculated?

Stars

48

Forks

4

Language

Python

License

Last pushed

Aug 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/gszfwsb/Data-Whisperer"

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