jsfs11/TurdusTrixBeagle-DARETIES-7B
TurdusTrixBeagle-DARETIES-7B is a 7 billion parameter language model created by jsfs11, built upon the Mistral-7B-v0.1 architecture. This model is a DARETIES merge of uakai/Turdus, CultriX/MergeTrix-7B-v2, and mlabonne/NeuralBeagle14-7B, designed to combine their respective strengths. It achieves an average score of 75.20 on the Open LLM Leaderboard, demonstrating strong performance across various reasoning and language understanding tasks. This model is suitable for general-purpose text generation and understanding where a 7B parameter model with a 4096-token context length is appropriate.
Loading preview...
TurdusTrixBeagle-DARETIES-7B Overview
TurdusTrixBeagle-DARETIES-7B is a 7 billion parameter language model developed by jsfs11, leveraging the Mistral-7B-v0.1 base architecture. This model is a result of a DARETIES merge, combining three distinct models: uakai/Turdus, CultriX/MergeTrix-7B-v2, and mlabonne/NeuralBeagle14-7B. The merging process aims to integrate the capabilities of these constituent models into a single, more robust offering.
Key Capabilities & Performance
This model demonstrates solid performance across a range of benchmarks, as evaluated on the Open LLM Leaderboard. It achieves an average score of 75.20, with notable results in specific areas:
- AI2 Reasoning Challenge (25-Shot): 73.46
- HellaSwag (10-Shot): 88.61
- MMLU (5-Shot): 64.89
- TruthfulQA (0-shot): 68.81
- Winogrande (5-shot): 85.16
- GSM8k (5-shot): 70.28
These scores indicate proficiency in reasoning, common sense, language understanding, and mathematical problem-solving.
Good For
- General-purpose text generation and comprehension tasks.
- Applications requiring a balance of performance and efficiency from a 7B parameter model.
- Scenarios where a 4096-token context window is sufficient for processing inputs.