thunlp/InfLLM

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

42
/ 100
Emerging

This project helps large language models (LLMs) understand and process extremely long text inputs, like those found in complex conversations or lengthy documents. It takes an existing LLM and allows it to maintain context over vast amounts of information, producing more coherent and relevant responses than standard methods. Anyone who works with LLMs and needs them to process very long conversations, extensive reports, or continuous data streams will find this useful.

395 stars. No commits in the last 6 months.

Use this if you need an existing large language model to comprehend and respond intelligently to input sequences that are hundreds of thousands or even a million tokens long without retraining the model.

Not ideal if your primary use case involves short, concise text inputs, as the benefits of long-sequence processing won't be realized.

long-context LLM conversational AI document analysis streaming data processing AI agent memory
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

395

Forks

39

Language

Python

License

MIT

Last pushed

Apr 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/thunlp/InfLLM"

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