nlpguy/AlloyIngotNeo

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Feb 13, 2024License:cc-by-nc-4.0Architecture:Transformer Open Weights Cold

nlpguy/AlloyIngotNeo is a 7 billion parameter language model developed by nlpguy, created by merging nlpguy/AlloyIngot and liminerity/Omningotex-7b-slerp using the SLERP method. This model demonstrates strong general reasoning capabilities, achieving an average score of 76.02 on the Open LLM Leaderboard across various benchmarks. With a 4096-token context length, it is suitable for tasks requiring robust understanding and generation.

Loading preview...

Model Overview

nlpguy/AlloyIngotNeo is a 7 billion parameter language model resulting from a strategic merge of two pre-trained models: nlpguy/AlloyIngot and liminerity/Omningotex-7b-slerp. This merge was performed using the SLERP (Spherical Linear Interpolation) method, a technique known for combining the strengths of different models while maintaining coherence.

Key Capabilities & Performance

This model exhibits strong performance across a range of general language understanding and reasoning tasks, as evidenced by its evaluation on the Open LLM Leaderboard. Key benchmark results include:

  • Avg. Score: 76.02
  • AI2 Reasoning Challenge (25-Shot): 72.87
  • HellaSwag (10-Shot): 88.99
  • MMLU (5-Shot): 64.61
  • TruthfulQA (0-shot): 75.95
  • Winogrande (5-shot): 84.29
  • GSM8k (5-shot): 69.45

These scores indicate a balanced capability in areas such as common sense reasoning, factual recall, and mathematical problem-solving.

When to Use This Model

AlloyIngotNeo is a versatile 7B model suitable for a variety of applications where a strong general-purpose language model is needed. Its balanced performance across multiple benchmarks makes it a good candidate for:

  • General text generation and completion
  • Question answering
  • Reasoning tasks
  • Applications requiring a compact yet capable model for deployment.