Model Overview

Weyaxi/OpenHermes-2.5-neural-chat-v3-2-Slerp is a 7 billion parameter language model developed by Weyaxi. This model was created using mergekit with the slerp (spherical linear interpolation) method, combining the strengths of teknium/OpenHermes-2.5-Mistral-7B and Intel/neural-chat-7b-v3-2. It is built upon the mistralai/Mistral-7B-v0.1 base model.

Key Capabilities & Performance

This model exhibits solid performance across a range of benchmarks, as evaluated on the Open LLM Leaderboard:

• Average Score: 70.2
• ARC (25-shot): 67.49
• HellaSwag (10-shot): 85.42
• MMLU (5-shot): 64.13
• TruthfulQA (0-shot): 61.05
• Winogrande (5-shot): 80.3
• GSM8K (5-shot): 63.08

Prompting

The model supports various prompt templates, with ChatML being the recommended format for optimal interaction. Examples for both OpenHermes-2.5-Mistral-7B and neural-chat-7b-v3-2 templates are provided for flexibility.

Important Note

Users are advised that a newer version, Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp, is available and recommended for use.