Model Overview

mayacinka/yam-jom-7B-slerp is a 7 billion parameter language model developed by mayacinka. It was created by merging two distinct models, eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2 and yam-peleg/Experiment26-7B, using the slerp (spherical linear interpolation) merge method. This technique combines the strengths of its base models to enhance overall performance.

Key Capabilities & Performance

This model exhibits strong performance across a variety of benchmarks, as evaluated on the Open LLM Leaderboard. It achieved an average score of 76.45, with notable results in:

• AI2 Reasoning Challenge (25-Shot): 72.70
• HellaSwag (10-Shot): 89.02
• MMLU (5-Shot): 64.64
• TruthfulQA (0-shot): 77.77
• Winogrande (5-shot): 84.69
• GSM8k (5-shot): 69.90

These scores indicate a balanced capability in reasoning, common sense, language understanding, and mathematical problem-solving.

Good For

• General-purpose natural language understanding and generation tasks.
• Applications requiring robust reasoning and common sense.
• Developers looking for a merged model that combines the strengths of its constituent parts for improved performance.