shadowml/WestBeagle-7B
WestBeagle-7B is a 7 billion parameter language model created by shadowml, formed by merging mlabonne/NeuralBeagle14-7B and FelixChao/WestSeverus-7B-DPO-v2 using a slerp merge method. This model demonstrates strong general reasoning capabilities, achieving an average score of 75.22 on the Open LLM Leaderboard. It is particularly well-suited for tasks requiring robust reasoning and general language understanding across various benchmarks.
Loading preview...
WestBeagle-7B: A Merged 7B Language Model
WestBeagle-7B is a 7 billion parameter language model developed by shadowml, created through a strategic merge of two base models: mlabonne/NeuralBeagle14-7B and FelixChao/WestSeverus-7B-DPO-v2. This merge was performed using the slerp method via LazyMergekit, combining the strengths of its constituent models to enhance overall performance.
Key Capabilities & Performance
This model exhibits strong performance across a range of benchmarks, as evaluated on the Open LLM Leaderboard. It achieved an average score of 75.22, with notable results in:
- AI2 Reasoning Challenge (25-Shot): 72.27
- HellaSwag (10-Shot): 88.29
- MMLU (5-Shot): 65.17
- TruthfulQA (0-shot): 71.71
- Winogrande (5-shot): 82.00
- GSM8k (5-shot): 71.87
These scores indicate its proficiency in reasoning, common sense, and general knowledge tasks. The model supports a context length of 4096 tokens.
When to Use WestBeagle-7B
WestBeagle-7B is a suitable choice for applications requiring a capable 7B parameter model with a balanced performance profile across various reasoning and language understanding tasks. Its merged architecture aims to leverage the best features of its base models, making it a versatile option for general-purpose text generation and analysis where a smaller, efficient model is preferred.