Model Overview

Weyaxi/TekniumAiroboros-Nebula-7B is a 7 billion parameter language model with an 8192-token context window, developed by Weyaxi. This model has been evaluated on the Hugging Face Open LLM Leaderboard, providing insights into its general performance across a range of academic benchmarks.

Key Capabilities

• General Language Understanding: Achieves an average score of 52.82 on the Open LLM Leaderboard, indicating broad comprehension abilities.
• Reasoning: Demonstrates performance in reasoning tasks with 57.17 on ARC (25-shot) and 55.25 on MMLU (5-shot).
• Common Sense: Scores 81.72 on HellaSwag (10-shot) and 73.24 on Winogrande (5-shot), reflecting common sense reasoning.
• Question Answering: Shows capabilities in question answering with 51.64 on TruthfulQA (0-shot) and 41.33 on DROP (3-shot).

Good For

• Applications requiring a general-purpose language model with a moderate parameter count.
• Tasks benefiting from a balance of reasoning, common sense, and factual recall.
• Developers looking for a 7B model with documented performance on standard benchmarks for initial evaluation and fine-tuning.