# 4k long context

An open-source large language model released by IBM under the Apache-2.0 license, reproducing Meta's Llama2-7B architecture and trained with 2T tokens of data.

Llama 2 is a series of generative text models open-sourced by Meta, including pre-trained and dialogue fine-tuned versions ranging from 7 billion to 70 billion parameters. This model is the 7 billion parameter dialogue-optimized version, fine-tuned with reinforcement learning for dialogue scenarios.