nlpguy/Hermes-low-tune-3.1
Hermes-low-tune-3.1 by nlpguy is a 7 billion parameter merged language model, built upon the teknium/OpenHermes-2.5-Mistral-7B base using a task arithmetic merge method. This model integrates several specialized components, including those focused on low-tune, topic neural, and code-oriented capabilities. It achieves an average score of 68.31 on the Open LLM Leaderboard, demonstrating balanced performance across reasoning, common sense, and mathematical tasks.
Loading preview...
Hermes-low-tune-3.1: A Merged 7B Language Model
This model, Hermes-low-tune-3.1, is a 7 billion parameter language model developed by nlpguy. It was created using the task arithmetic merge method with teknium/OpenHermes-2.5-Mistral-7B as its base model.
Key Capabilities & Merge Details
The model integrates capabilities from several distinct models, enhancing its overall performance and versatility. The merge incorporated:
nlpguy/Hermes-low-tune-2charlesdedampierre/TopicNeuralHermes-2.5-Mistral-7Bopenaccess-ai-collective/openhermes-2_5-dpo-no-robotsflemmingmiguel/Mistrality-7Bbeowolx/MistralHermes-CodePro-7B-v1
Each merged component contributed with a weight of 0.2, indicating a balanced integration of their respective strengths across all 32 layers.
Performance Benchmarks
Evaluated on the Open LLM Leaderboard, Hermes-low-tune-3.1 demonstrates solid performance with an average score of 68.31. Notable scores include:
- AI2 Reasoning Challenge (25-Shot): 65.44
- HellaSwag (10-Shot): 84.60
- MMLU (5-Shot): 64.13
- TruthfulQA (0-shot): 53.59
- Winogrande (5-shot): 78.61
- GSM8k (5-shot): 63.46
These results suggest a well-rounded model suitable for tasks requiring general reasoning, common sense, and mathematical problem-solving. Detailed evaluation results are available on the Hugging Face Open LLM Leaderboard.