Model Overview

Weyaxi/Luban-Platypus2-13B-QLora-0.80-epoch is a 13 billion parameter language model created by merging two distinct models: ai-business/Luban-13B and Platypus2-13B-QLoRA-0.80-epoch. This fusion aims to combine the strengths of both base models, offering a versatile tool for various natural language processing tasks.

Performance Benchmarks

Evaluated on the Open LLM Leaderboard, this model achieves a competitive average score of 63.94. Key performance metrics include:

• Avg.: 63.94
• ARC (25-shot): 60.24
• HellaSwag (10-shot): 82.22
• MMLU (5-shot): 58.03
• TruthfulQA (0-shot): 55.26

Detailed evaluation results, including additional metrics like Winogrande (75.37), GSM8K (0.91), and DROP (12.95), are available on the Open LLM Leaderboard details page.

Use Cases

Given its balanced performance across various benchmarks, this model is suitable for general-purpose applications requiring robust language understanding and generation. Its 13B parameter count makes it a capable option for tasks where larger models might be overkill, but more nuanced understanding is needed than smaller models can provide.