darkc0de/Xortron24DPO

Hugging Face
TEXT GENERATIONConcurrency Cost:2Model Size:24BQuant:FP8Ctx Length:32kPublished:Apr 16, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

darkc0de/Xortron24DPO is a 24 billion parameter Mistral-based language model, fine-tuned from TroyDoesAI/BlackSheep-24B. Developed by darkc0de, this model was trained using Unsloth and Huggingface's TRL library, achieving a 2x faster training speed. It is designed for general language tasks, leveraging its Mistral architecture for efficient processing.

Loading preview...

Overview

darkc0de/Xortron24DPO is a 24 billion parameter language model developed by darkc0de. It is fine-tuned from the TroyDoesAI/BlackSheep-24B model, utilizing a Mistral-based architecture. A key aspect of its development is the integration of Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.

Key Characteristics

  • Parameter Count: 24 billion parameters.
  • Base Model: Fine-tuned from TroyDoesAI/BlackSheep-24B, indicating a strong foundation.
  • Training Efficiency: Leverages Unsloth for significantly accelerated training, making it a potentially more cost-effective or rapidly iterated model.
  • Context Length: Supports a context length of 32768 tokens.

Potential Use Cases

Given its Mistral-based architecture and 24B parameters, Xortron24DPO is suitable for a range of general-purpose language tasks, including:

  • Text generation and completion.
  • Summarization.
  • Question answering.
  • Conversational AI applications.