Aleteian/Sexpedition-MS3.2-24B

Hugging Face
TEXT GENERATIONConcurrent Unit Cost:2Model Size:24BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 15, 2025Architecture:Transformer0.0K Featherless Exclusive Warm

Aleteian/Sexpedition-MS3.2-24B is a 24 billion parameter language model created by Aleteian, formed by merging ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0 and Doctor-Shotgun/MS3.2-24B-Magnum-Diamond using the arcee_fusion method. This model is designed for general text generation tasks, leveraging its 24B parameters and 32768 token context length for robust performance. Its architecture is optimized for diverse applications requiring substantial linguistic understanding and generation capabilities.

Loading preview...

Sexpedition-MS3.2-24B Overview

Aleteian/Sexpedition-MS3.2-24B is a 24 billion parameter language model developed by Aleteian. It was created through a strategic merge of two distinct models: ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0 and Doctor-Shotgun/MS3.2-24B-Magnum-Diamond. This merging process utilized the arcee_fusion method within LazyMergekit, aiming to combine the strengths of its constituent models.

Key Capabilities

  • Merged Architecture: Benefits from the combined knowledge and capabilities of its base models, potentially offering a more balanced and robust performance across various tasks.
  • Parameter Scale: With 24 billion parameters, it is well-suited for complex language understanding and generation tasks.
  • Context Length: Supports a substantial context window of 32768 tokens, enabling it to process and generate longer, more coherent texts.
  • Flexible Deployment: Designed for straightforward integration into Python environments using the Hugging Face transformers library, supporting bfloat16 and float16 precision for efficient inference.

Good For

  • General Text Generation: Capable of handling a wide array of text generation prompts, from creative writing to informative responses.
  • Complex Query Handling: Its large parameter count and context window make it suitable for understanding and responding to intricate user queries.
  • Research and Experimentation: Provides a solid base for developers and researchers looking to explore merged model performance and fine-tune for specific applications.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p