datamllab/LongLM

[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

43
/ 100
Emerging

This project helps anyone working with Large Language Models (LLMs) to process much longer documents, conversations, or data sequences than typically possible. It takes an existing LLM, like Llama or Gemma, and extends its ability to understand and generate text based on significantly more input. This is for developers and researchers who build applications using LLMs and need them to handle extensive context without expensive retraining.

666 stars. No commits in the last 6 months.

Use this if you need an existing Large Language Model to process very long texts, such as entire books, lengthy research papers, or extensive chat histories, without requiring fine-tuning.

Not ideal if your current LLM applications already handle context windows of sufficient length or if you are not comfortable modifying model code.

Large Language Models LLM application development natural language processing AI research long-context AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

666

Forks

60

Language

Python

License

MIT

Last pushed

Jun 01, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/datamllab/LongLM"

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