Overview

MSL7/INEX4-7b is a 7 billion parameter language model developed by Liminerity. It was constructed using a multi-stage slerp merging process via MergeKit, combining distinct components from liminerity/Ingot-7b-slerp-7-forged and yam-peleg/Experiment26-7B.

Key Capabilities & Performance

This model exhibits robust performance across various benchmarks, as evaluated on the Open LLM Leaderboard. It achieved an average score of 75.84, with notable results in:

• AI2 Reasoning Challenge (25-Shot): 72.95
• HellaSwag (10-Shot): 88.79
• MMLU (5-Shot): 64.70
• TruthfulQA (0-shot): 74.42
• Winogrande (5-shot): 83.90
• GSM8k (5-shot): 70.28

Use Cases

Given its balanced performance across reasoning, common sense, and language understanding tasks, INEX4-7b is well-suited for general-purpose applications requiring strong analytical and generative capabilities. Its 7B parameter size makes it efficient for deployment while maintaining competitive performance.