Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Linear
Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Linear is a 34 billion parameter language model created by Weyaxi, formed by a linear merge of Nous-Hermes-2-Yi-34B and SUS-Chat-34B. This model is designed for general chat applications, leveraging the combined strengths of its base models. It achieves an average score of 73.69 on the Open LLM Leaderboard across various reasoning and language understanding benchmarks.
Loading preview...
Model Overview
Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Linear is a 34 billion parameter language model developed by Weyaxi. It was created using a linear merge method via mergekit, combining two distinct base models: Nous-Hermes-2-Yi-34B (with a weight of 0.5) and SUS-Chat-34B (with a weight of 0.3). This merging strategy aims to integrate the capabilities of both foundational models into a single, more versatile chat-oriented model.
Key Capabilities & Performance
This model demonstrates strong performance across a range of benchmarks, as evaluated on the Open LLM Leaderboard. Its average score is 73.69, indicating robust general language understanding and reasoning abilities. Specific benchmark results include:
- AI2 Reasoning Challenge (25-Shot): 66.38
- HellaSwag (10-Shot): 84.94
- MMLU (5-Shot): 76.82
- TruthfulQA (0-shot): 59.19
- Winogrande (5-shot): 82.79
- GSM8k (5-shot): 72.02
Use Cases
Given its strong performance across diverse benchmarks, Nous-Hermes-2-SUS-Chat-34B-Linear is well-suited for general-purpose conversational AI applications, complex reasoning tasks, and language understanding scenarios where a balanced performance profile is desired. Its 32K context length further supports handling longer interactions and more detailed prompts.