Overview

StrangeMerges_26-7B-dare_ties is a 7 billion parameter language model developed by Gille. It was created through a merge of two existing models, paulml/OGNO-7B and Gille/StrangeMerges_25-7B-dare_ties, utilizing the DARE TIES merging method. The base model for this merge was Gille/StrangeMerges_21-7B-slerp.

Key Capabilities & Performance

This model demonstrates competitive performance on the Open LLM Leaderboard, achieving an average score of 76.19. Specific benchmark results include:

• AI2 Reasoning Challenge (25-Shot): 72.95
• HellaSwag (10-Shot): 89.00
• MMLU (5-Shot): 64.35
• TruthfulQA (0-shot): 76.39
• Winogrande (5-shot): 84.45
• GSM8k (5-shot): 69.98

Good For

• General text generation and completion tasks.
• Applications requiring strong reasoning and common sense understanding.
• Use cases benefiting from a 7B parameter model with a 4096-token context window.
• Developers looking for a merged model with a balanced performance profile across various benchmarks.