AI-B/UTENA-7B-V3

AI-B/UTENA-7B-V3 is a 7 billion parameter language model developed by AI-B, created by merging UTENA-7B-UNA-V2 and UTENA-7B-NSFW-V2 using the slerp method. This model achieves an average score of 67.42 on the Open LLM Leaderboard, demonstrating capabilities across various benchmarks including reasoning, common sense, and language understanding. It is designed for general-purpose applications requiring a balanced performance profile.