kaitchup/Mayonnaise-4in1-02
Mayonnaise-4in1-02 is a 7 billion parameter causal language model developed by The Kaitchup, built using a TIES-merging technique on a Mistral-7B-v0.1 base. This model integrates multiple specialized models to achieve strong performance across various benchmarks, including an average score of 75.21 on the Open LLM Leaderboard. It is designed for general English language tasks, demonstrating capabilities in reasoning, common sense, and question answering.
Loading preview...
Model Overview
Mayonnaise-4in1-02 is a 7 billion parameter causal language model developed by The Kaitchup. It is an ensemble model created using the TIES-merging technique with MergeKit, based on the mistralai/Mistral-7B-v0.1 architecture. This model combines the strengths of several fine-tuned models, including mncai/mistral-7b-dpo-v5, flemmingmiguel/MBX-7B, and BarryFutureman/NeuralTurdusVariant1-7B, to enhance its overall performance.
Key Capabilities & Performance
The model demonstrates strong general-purpose language understanding and generation capabilities, as evidenced by its performance on the Open LLM Leaderboard. Key evaluation results include:
- Avg. Score: 75.21
- AI2 Reasoning Challenge (25-Shot): 73.38
- HellaSwag (10-Shot): 88.51
- MMLU (5-Shot): 64.89
- TruthfulQA (0-shot): 69.04
- Winogrande (5-shot): 84.37
- GSM8k (5-shot): 71.04
These scores indicate proficiency in reasoning, common sense, factual recall, and mathematical problem-solving. The model is licensed under Apache 2.0.
When to Use This Model
This model is suitable for a variety of English NLP tasks where a balanced performance across different benchmarks is desired. Its TIES-merging approach aims to leverage the specialized knowledge of its constituent models, making it a robust option for applications requiring:
- General text generation and understanding.
- Reasoning and logical inference.
- Question answering and factual recall.
- Common sense understanding.
Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.