Gille/StrangeMerges_9-7B-dare_ties
Gille/StrangeMerges_9-7B-dare_ties is a 7 billion parameter language model created by Gille, formed by merging leveldevai/TurdusBeagle-7B and samir-fama/FernandoGPT-v1 using the dare_ties method. This model demonstrates strong general performance, achieving an average score of 73.32 on the Open LLM Leaderboard, with notable results in reasoning and common sense benchmarks. It is designed for general-purpose language understanding and generation tasks, offering a balanced performance profile.
Loading preview...
Model Overview
Gille/StrangeMerges_9-7B-dare_ties is a 7 billion parameter language model developed by Gille. It is a product of a merge operation using the dare_ties method, combining the strengths of two base models: leveldevai/TurdusBeagle-7B and samir-fama/FernandoGPT-v1. This merging approach aims to synthesize and enhance the capabilities of its constituent models.
Performance Highlights
Evaluated on the Open LLM Leaderboard, StrangeMerges_9-7B-dare_ties achieved an average score of 73.32. Key performance metrics include:
- AI2 Reasoning Challenge (25-Shot): 70.31
- HellaSwag (10-Shot): 87.46
- MMLU (5-Shot): 65.08
- TruthfulQA (0-shot): 65.08
- Winogrande (5-shot): 81.37
- GSM8k (5-shot): 70.58
These results indicate a balanced capability across various tasks, including reasoning, common sense, and mathematical problem-solving.
Use Cases
This model is suitable for a range of general-purpose natural language processing applications where a 7B parameter model with solid performance is required. Its balanced benchmark scores suggest proficiency in:
- General text generation and completion
- Question answering and information retrieval
- Reasoning-based tasks
- Common sense understanding