ReadyArt/4.2.0-Broken-Tutu-24b

TEXT GENERATIONConcurrency Cost:2Model Size:24BQuant:FP8Ctx Length:32kPublished:Oct 20, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

ReadyArt/4.2.0-Broken-Tutu-24b is a 24 billion parameter language model created by ReadyArt, merged using the DARE TIES method with TheDrummer/Cydonia-24B-v4.2.0 as its base. This model integrates components from several 24B models, including TroyDoesAI/BlackSheep-24B and multiple ReadyArt models, to enhance its overall capabilities. It features a 32768 token context length, making it suitable for applications requiring extensive contextual understanding and generation.

Loading preview...

Model Overview

ReadyArt/4.2.0-Broken-Tutu-24b is a 24 billion parameter language model resulting from a sophisticated merge of several pre-trained models. Developed by ReadyArt, this model leverages the DARE TIES merge method, utilizing TheDrummer/Cydonia-24B-v4.2.0 as its foundational base.

Merge Details

The model incorporates contributions from a diverse set of 24B parameter models, each weighted to optimize performance:

This specific merging strategy aims to combine the strengths of these individual models, potentially leading to improved generalization and performance across various tasks. The model supports a substantial context length of 32768 tokens, enabling it to process and generate longer, more coherent texts.

Key Characteristics

  • Parameter Count: 24 billion parameters.
  • Context Length: 32768 tokens, suitable for complex, multi-turn conversations or detailed document analysis.
  • Merge Method: Utilizes the DARE TIES method for combining model weights, a technique known for its effectiveness in creating robust merged models.

Potential Use Cases

Given its architecture and context window, this model is well-suited for applications requiring:

  • Advanced text generation and comprehension.
  • Handling long-form content, such as summarization of extensive documents or detailed creative writing.
  • Tasks benefiting from the combined capabilities of its constituent models.