darkc0de/BlackXorDolphTronGOAT

Hugging Face
TEXT GENERATIONConcurrency Cost:2Model Size:24BQuant:FP8Ctx Length:32kPublished:May 3, 2025License:wtfplArchitecture:Transformer0.0K Warm

darkc0de/BlackXorDolphTronGOAT is a 24 billion parameter language model created by darkc0de, built through an experimental stacking and shuffling process using the arcee_fusion method in mergekit. This model is a personal experiment in merging multiple base models to explore novel architectural combinations. With a 32768 token context length, it aims to leverage merged capabilities for diverse language tasks.

Loading preview...

Model Overview

darkc0de/BlackXorDolphTronGOAT is a 24 billion parameter experimental language model developed by darkc0de. It was constructed using the mergekit tool, specifically employing the arcee_fusion merge method. This approach involves stacking and shuffling multiple base models to create a unique combined architecture.

Key Characteristics

  • Parameter Count: 24 billion parameters, offering substantial capacity for complex language understanding and generation.
  • Context Length: Supports a context window of 32768 tokens, enabling the processing of lengthy inputs and maintaining coherence over extended conversations or documents.
  • Experimental Architecture: Represents a personal experiment in model merging, focusing on the arcee_fusion method to explore new ways of combining existing models.

Potential Use Cases

Given its experimental nature and large parameter count, BlackXorDolphTronGOAT could be suitable for:

  • Research and Development: Ideal for researchers interested in model merging techniques and their impact on performance.
  • Complex Language Tasks: Its substantial context window and parameter size suggest potential for tasks requiring deep contextual understanding, such as long-form content generation, detailed summarization, or advanced question answering.
  • Exploratory Applications: Developers looking for a unique model with potentially novel emergent properties from its merged architecture might find it useful for various NLP applications.