declare-lab/instruct-eval

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

41
/ 100
Emerging

This project helps AI researchers and practitioners evaluate how well instruction-tuned large language models (LLMs) like Alpaca and Flan-T5 perform on various tasks they haven't seen before. You provide a model, and it outputs quantitative scores across standard academic benchmarks. This is ideal for those comparing different LLMs to understand their generalization capabilities.

552 stars. No commits in the last 6 months.

Use this if you need to quantitatively benchmark and compare the performance of various instruction-tuned large language models on unseen tasks using established academic benchmarks.

Not ideal if you are looking to fine-tune a model or analyze specific qualitative aspects of model outputs beyond standard benchmark metrics.

AI model evaluation natural language processing research large language model benchmarking machine learning performance assessment LLM development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

552

Forks

44

Language

Python

License

Apache-2.0

Last pushed

Mar 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/declare-lab/instruct-eval"

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