Weyaxi/Nova-13B-50-step

TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kPublished:Sep 5, 2023License:llama2Architecture:Transformer Open Weights Cold

Weyaxi/Nova-13B-50-step is a 13 billion parameter language model developed by Weyaxi, featuring a 4096-token context length. This model demonstrates a balanced performance across various benchmarks, including an average score of 48.93 on the Open LLM Leaderboard. It is suitable for general-purpose language understanding and generation tasks, with notable scores in ARC and HellaSwag evaluations.

Loading preview...

Model Overview

Weyaxi/Nova-13B-50-step is a 13 billion parameter language model with a 4096-token context window. Developed by Weyaxi, this model has been evaluated on the Open LLM Leaderboard, showcasing its capabilities across a range of tasks.

Key Performance Metrics

The model's performance is summarized by its average score of 48.93 on the Open LLM Leaderboard. Specific benchmark results include:

  • ARC (25-shot): 61.6
  • HellaSwag (10-shot): 82.31
  • MMLU (5-shot): 57.27
  • TruthfulQA (0-shot): 51.53
  • Winogrande (5-shot): 76.56
  • GSM8K (5-shot): 4.4
  • DROP (3-shot): 8.82

These scores indicate a solid foundation for tasks requiring general knowledge, common sense reasoning, and language comprehension.

Potential Use Cases

Given its balanced performance, Nova-13B-50-step is well-suited for:

  • General text generation and completion
  • Question answering based on common knowledge
  • Reasoning tasks, as indicated by its ARC score
  • Applications requiring robust language understanding