seyf1elislam/WestKunai-XS-7b
WestKunai-XS-7b is a 7 billion parameter language model developed by seyf1elislam, created through a merge of seyf1elislam/WestKunai-Hermes-7b and seyf1elislam/KuTrix-7b using the slerp method. This merged model demonstrates a strong average performance of 74.18 on the Open LLM Leaderboard, with notable scores in reasoning and common sense benchmarks. It is designed for general language generation tasks, leveraging the combined strengths of its constituent models.
Loading preview...
Model Overview
WestKunai-XS-7b is a 7 billion parameter language model developed by seyf1elislam, resulting from a strategic merge of two pre-trained models: seyf1elislam/WestKunai-Hermes-7b and seyf1elislam/KuTrix-7b. This merge was performed using the slerp (spherical linear interpolation) method, as configured in Mergekit, to combine their respective strengths across different layers.
Key Capabilities & Performance
The model has been evaluated on the Open LLM Leaderboard, achieving a solid average score of 74.18. Specific benchmark results highlight its proficiency in various areas:
- AI2 Reasoning Challenge (25-Shot): 71.08
- HellaSwag (10-Shot): 87.86
- MMLU (5-Shot): 65.42
- TruthfulQA (0-shot): 68.01
- Winogrande (5-shot): 82.87
- GSM8k (5-shot): 69.83
These scores indicate a balanced capability across reasoning, common sense, and language understanding tasks. The model supports a context length of 4096 tokens.
Usage and Availability
Quantized versions of WestKunai-XS-7b are available in GGUF format for efficient deployment. The model can be easily integrated into projects using the Hugging Face transformers library, with a provided Python example demonstrating text generation.