nlpguy/Hermes-low-tune-3

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Jan 6, 2024License:apache-2.0Architecture:Transformer Open Weights Cold

nlpguy/Hermes-low-tune-3 is a 7 billion parameter language model created by nlpguy, merged using the SLERP method from nlpguy/Hermes-low-tune-2 and openaccess-ai-collective/DPOpenHermes-7B-v2. This model features a 4096-token context length and demonstrates strong general performance across various benchmarks, including an average score of 69.25 on the Open LLM Leaderboard. It is suitable for general-purpose language understanding and generation tasks.

Loading preview...

Model Overview

nlpguy/Hermes-low-tune-3 is a 7 billion parameter language model developed by nlpguy. It was created by merging two pre-trained models, nlpguy/Hermes-low-tune-2 and openaccess-ai-collective/DPOpenHermes-7B-v2, using the SLERP merge method via mergekit.

Performance Highlights

This model has been evaluated on the Open LLM Leaderboard, achieving a competitive average score of 69.25. Key benchmark results include:

  • AI2 Reasoning Challenge (25-Shot): 66.21
  • HellaSwag (10-Shot): 84.99
  • MMLU (5-Shot): 63.74
  • TruthfulQA (0-shot): 57.94
  • Winogrande (5-shot): 78.77
  • GSM8k (5-shot): 63.84

Detailed evaluation results are available here.

Use Cases

Given its balanced performance across various reasoning and language understanding tasks, Hermes-low-tune-3 is well-suited for a range of general-purpose applications requiring robust language capabilities, such as:

  • Text generation
  • Question answering
  • Summarization
  • Reasoning tasks