Victorwz/LongMem

Official implementation of our NeurIPS 2023 paper "Augmenting Language Models with Long-Term Memory".

44
/ 100
Emerging

This project offers a way to enhance large language models (LLMs) so they can better handle very long texts and recall relevant information from them. It takes a base LLM and long textual data, producing a more capable LLM that can maintain context and consistency over extended interactions. AI/ML researchers and practitioners working on advanced language understanding applications would find this useful.

822 stars. No commits in the last 6 months.

Use this if you are developing or fine-tuning large language models and need them to process, understand, and generate content effectively over extremely long documents or conversational histories.

Not ideal if you are looking for an off-the-shelf application to use directly without deep technical understanding of language model development.

large-language-models natural-language-processing AI-research model-training context-window-extension
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

822

Forks

74

Language

Python

License

Apache-2.0

Last pushed

Mar 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Victorwz/LongMem"

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