Discover the Treasure Hidden in Your Technology Box

Start finding artificial intelligence tools that will help you do everything you can imagine.

Login TR Türkçe
LongLLaMa

LongLLaMa Add to favorites

Upvote

Last update time : 2025-09-24 10:47:30

A large language model with an extended context window, designed to understand and process extensive text contexts.

LongLLaMA is an extended large language model capable of processing text contexts up to 256,000 tokens. It is based on OpenLLaMA and fine-tuned using the Focused Transformer (FoT) method. The core innovation of this model is its ability to manage contexts significantly longer than its training data, making it especially useful for tasks that demand extensive contextual understanding. A smaller 3B base variant of LongLLaMA is available under an Apache 2.0 license. The repository also provides code for instruction tuning and continued pre-training with FoT, allowing for easy integration into Hugging Face for various natural language processing tasks.

Pricing : Open Source

Web Address : LongLLaMa

Tags : large language model long context natural language processing artificial intelligence OpenLLaMA


See all