OxytocinErosEngineeringF1-7B-slerp Overview

OxytocinErosEngineeringF1-7B-slerp is a 7 billion parameter language model developed by weezywitasneezy. It is a product of merging two distinct models, ChaoticNeutrals/Eris_Remix_7B and Virt-io/Erebus-Holodeck-7B, utilizing the slerp (spherical linear interpolation) merge method. This approach combines the strengths of its base models to create a new, enhanced model.

Key Capabilities & Performance

This model has been evaluated on the Open LLM Leaderboard, achieving a competitive average score of 69.22. Specific performance metrics include:

• AI2 Reasoning Challenge (25-Shot): 67.15
• HellaSwag (10-Shot): 86.0
• MMLU (5-Shot): 64.73
• TruthfulQA (0-shot): 54.54
• Winogrande (5-shot): 81.14
• GSM8k (5-shot): 61.79

These scores indicate a balanced performance across various benchmarks, including reasoning, common sense, factual recall, and mathematical problem-solving. The model supports a context length of 4096 tokens.

Good For

• General-purpose text generation: Capable of generating coherent and contextually relevant text for a wide range of prompts.
• Conversational AI: Its performance on reasoning and common sense tasks makes it suitable for developing interactive agents.
• Experimentation with merged models: Provides a practical example of the slerp merge method's application and its resulting performance characteristics.