nlpguy/Hermes-low-tune

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

nlpguy/Hermes-low-tune is a 7 billion parameter language model created by nlpguy, merged using the SLERP method from openaccess-ai-collective/dpopenhermes-alpha-v0 and simonveitner/Math-OpenHermes-2.5-Mistral-7B. This model is designed for general language tasks, demonstrating strong performance across various reasoning and common sense benchmarks. With a 4096-token context length, it offers a balanced capability for diverse applications.

Loading preview...

nlpguy/Hermes-low-tune: A Merged 7B Language Model

nlpguy/Hermes-low-tune is a 7 billion parameter language model developed by nlpguy, created by merging two pre-trained models: openaccess-ai-collective/dpopenhermes-alpha-v0 and simonveitner/Math-OpenHermes-2.5-Mistral-7B. This merge was performed using the SLERP (Spherical Linear Interpolation) method, with a specific configuration that blended the models' layers.

Key Capabilities & Performance

This model demonstrates solid performance across a range of benchmarks, as evaluated on the Open LLM Leaderboard. Its average score is 67.18, indicating a well-rounded capability for general language understanding and generation tasks. Notable scores include:

  • AI2 Reasoning Challenge (25-Shot): 63.99
  • HellaSwag (10-Shot): 83.75
  • MMLU (5-Shot): 63.60
  • TruthfulQA (0-shot): 51.37
  • Winogrande (5-shot): 77.90
  • GSM8k (5-shot): 62.47

These results suggest proficiency in common sense reasoning, multiple-choice question answering, and mathematical problem-solving.

Good For

  • General-purpose language generation and understanding tasks.
  • Applications requiring a balance of reasoning and common sense.
  • Use cases where a 7B parameter model with a 4096-token context length is suitable for deployment.