Model Overview

Gille/StrangeMerges_5-7B-ties is a 7 billion parameter language model developed by Gille, created using the TIES merging method. It is built upon the mncai/mistral-7b-dpo-v5 as its base model, incorporating contributions from Gille/StrangeMerges_1-7B-slerp and BarryFutureman/NeuralTurdusVariant1-7B to enhance its capabilities.

Key Capabilities & Performance

This model demonstrates robust performance across a range of benchmarks, as evaluated on the Hugging Face Open LLM Leaderboard. It achieves an average score of 73.89, indicating strong general language understanding and reasoning abilities. Specific benchmark results include:

• AI2 Reasoning Challenge (25-Shot): 71.67
• HellaSwag (10-Shot): 87.88
• MMLU (5-Shot): 64.91
• TruthfulQA (0-shot): 66.37
• Winogrande (5-shot): 83.66
• GSM8k (5-shot): 68.84

These scores highlight its proficiency in tasks requiring common sense reasoning, factual recall, and mathematical problem-solving.

Use Cases

StrangeMerges_5-7B-ties is suitable for a variety of general-purpose natural language processing applications, including:

• Text generation and completion
• Question answering
• Summarization
• Chatbot development
• Reasoning tasks