Nous Llama 2
About
The Nous Llama 2 family, developed by Nous Research, consists of large language models that include various sizes such as 7B, 13B, and 70B parameters. These models are fine-tuned on an extensive dataset of over 300,000 instructions, leveraging the Llama 2 architecture. They are distinguished by their ability to generate lengthy responses with a low hallucination rate, as well as the lack of OpenAI censorship in their training data. The training process predominantly utilized synthetic outputs from GPT-4, complemented by data from open-source datasets. Available on Hugging Face, the Nous Llama 2 models are versatile for diverse language tasks, ranging from creative text generation to complex instruction following 148.