SkkuDS-DPO-72B-v4 is a 72.3 billion parameter instruction-tuned causal language model developed by logicker, based on the Qwen1.5 architecture. It features stable support for a 32K context length and enhanced multilingual capabilities. This model is fine-tuned using DPO on the Intel/orca_dpo_pairs dataset, making it suitable for a wide range of general-purpose conversational AI tasks.
No reviews yet. Be the first to review!
Hugging Face