datamllab/LongLM
[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
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.
Stars
666
Forks
60
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
ZHZisZZ/dllm
dLLM: Simple Diffusion Language Modeling
pengzhangzhi/Open-dLLM
Open diffusion language model for code generation — releasing pretraining, evaluation,...
EnnengYang/Awesome-Model-Merging-Methods-Theories-Applications
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM...
THUDM/LongWriter
[ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
AIoT-MLSys-Lab/SVD-LLM
[ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2