weezywitasneezy/OxytocinErosEngineeringFX-7B-slerp
weezywitasneezy/OxytocinErosEngineeringFX-7B-slerp is a 7 billion parameter language model created by weezywitasneezy, built by merging four Mistral 7B-based models using the slerp method. This model achieves an average score of 70.28 on the Open LLM Leaderboard, demonstrating strong performance across various reasoning and language understanding tasks. It is particularly suited for general-purpose text generation and understanding where a balanced performance across multiple benchmarks is desired.
Loading preview...
Overview
OxytocinErosEngineeringFX-7B-slerp is a 7 billion parameter language model developed by weezywitasneezy. It is a complex merge of four distinct Mistral 7B-based models: Eris_Remix_7B, Erebus-Holodeck-7B, Eros_Prodigadigm_7B, and Mika-7B. The model was created using the slerp (spherical linear interpolation) merge method, combining two intermediate slerp merges, OxytocinErosEngineeringF1-7B-slerp and OxytocinErosEngineeringF2-7B-slerp.
Key Capabilities & Performance
This model demonstrates robust performance across a range of benchmarks, achieving an average score of 70.28 on the Open LLM Leaderboard. Specific benchmark results include:
- AI2 Reasoning Challenge (25-Shot): 66.98
- HellaSwag (10-Shot): 86.48
- MMLU (5-Shot): 64.14
- TruthfulQA (0-shot): 65.25
- Winogrande (5-shot): 81.45
- GSM8k (5-shot): 57.39
Usage
The model supports a context length of 4096 tokens and can be easily integrated into Python applications using the Hugging Face transformers library for text generation tasks. Its bfloat16 dtype configuration is optimized for efficient inference.