princeton-nlp/Llama-3-Instruct-8B-KTO

The princeton-nlp/Llama-3-Instruct-8B-KTO is an 8 billion parameter instruction-tuned language model developed by princeton-nlp, based on the Llama-3 architecture. This model incorporates KTO (Kahneman-Tversky Optimization) for preference alignment, distinguishing it from standard instruction-tuned models. It is designed for general conversational AI tasks, leveraging its 8192-token context length for coherent and extended interactions.