Weyaxi/MythoMix-Platypus2-13B-QLoRA-0.80-epoch

TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kLicense:llama2Architecture:Transformer Open Weights Cold

Weyaxi/MythoMix-Platypus2-13B-QLoRA-0.80-epoch is a 13 billion parameter language model, a merge of Gryphe/MythoMix-L2-13b and Platypus2-13B-QLoRA-0.80-epoch. This model demonstrates a balanced performance across various benchmarks, including reasoning, common sense, and language understanding tasks. With a context length of 4096 tokens, it is suitable for general-purpose language generation and comprehension applications.

Loading preview...

Model Overview

Weyaxi/MythoMix-Platypus2-13B-QLoRA-0.80-epoch is a 13 billion parameter language model created by Weyaxi. It is a strategic merge of two distinct models: Gryphe/MythoMix-L2-13b and Platypus2-13B-QLoRA-0.80-epoch. This merging approach aims to combine the strengths of its constituent models, offering a versatile tool for various natural language processing tasks.

Performance Highlights

The model's performance has been evaluated on the Open LLM Leaderboard, showcasing its capabilities across several key metrics. Detailed results are available here.

  • Average Score: 52.91
  • ARC (25-shot): 60.32
  • HellaSwag (10-shot): 83.72
  • MMLU (5-shot): 55.74
  • TruthfulQA (0-shot): 52.18
  • Winogrande (5-shot): 75.53
  • GSM8K (5-shot): 0.91 (mathematical reasoning)
  • DROP (3-shot): 41.98 (reading comprehension)

Use Cases

Given its balanced performance across a range of benchmarks, MythoMix-Platypus2-13B-QLoRA-0.80-epoch is well-suited for applications requiring:

  • General text generation: Creating coherent and contextually relevant text.
  • Question answering: Responding to queries based on provided context.
  • Reasoning tasks: Handling tasks that involve logical deduction and problem-solving, as indicated by its ARC and MMLU scores.
  • Common sense understanding: Demonstrated by its HellaSwag and Winogrande scores.