gate369/Nexim-7b
Nexim-7b is a 7 billion parameter language model developed by gate369, created by merging liminerity/m3 and liminerity/M7-7b using the slerp method. This model demonstrates strong general reasoning capabilities, achieving an average score of 76.53 on the Open LLM Leaderboard. It performs well across various benchmarks including HellaSwag, Winogrande, and GSM8k, making it suitable for a range of general-purpose language tasks.
Loading preview...
Nexim-7b: A Merged 7B Language Model
Nexim-7b is a 7 billion parameter model developed by gate369, constructed through a merge of two base models: liminerity/m3 and liminerity/M7-7b. This merge was performed using the slerp method via mergekit, combining the strengths of its constituent models.
Key Capabilities & Performance
Nexim-7b demonstrates robust performance across a suite of benchmarks, achieving an average score of 76.53 on the Open LLM Leaderboard. Specific benchmark results include:
- AI2 Reasoning Challenge (25-Shot): 73.04
- HellaSwag (10-Shot): 89.10
- MMLU (5-Shot): 64.48
- TruthfulQA (0-shot): 77.68
- Winogrande (5-shot): 84.77
- GSM8k (5-shot): 70.13
These scores indicate strong general reasoning, common sense, and mathematical problem-solving abilities for a model of its size.
Ideal Use Cases
Nexim-7b is well-suited for applications requiring a capable general-purpose language model, particularly where a balance between performance and computational resources is desired. Its strong benchmark results suggest it can be effectively used for:
- General text generation and understanding tasks.
- Reasoning and logical inference.
- Question answering and summarization.
- Educational applications requiring problem-solving (e.g., math word problems).