SvalTek/Arcadia-12B-Fusion-V2

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kPublished:May 27, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

SvalTek/Arcadia-12B-Fusion-V2 is a 12 billion parameter Mistral-based language model developed by SvalTek, fine-tuned from SvalTek/Arcadia-12B-Fusion. This model was optimized for training efficiency using Unsloth and Huggingface's TRL library, offering a 32768 token context length. It is designed for general language tasks, leveraging its efficient training methodology.

Loading preview...

Overview

SvalTek/Arcadia-12B-Fusion-V2 is a 12 billion parameter language model developed by SvalTek. It is a fine-tuned variant of the SvalTek/Arcadia-12B-Fusion model, built upon the Mistral architecture. A key characteristic of this model is its training efficiency, having been fine-tuned using the Unsloth library in conjunction with Huggingface's TRL library, which enabled a 2x faster training process.

Key Capabilities

  • Efficient Training: Leverages Unsloth for significantly faster fine-tuning.
  • Mistral Architecture: Benefits from the robust performance characteristics of the Mistral base model.
  • Context Length: Supports a substantial context window of 32768 tokens, suitable for processing longer inputs.

Good For

  • Developers seeking a 12B parameter model with an efficient training lineage.
  • Applications requiring a model with a large context window for complex tasks.
  • General language generation and understanding tasks where the Mistral architecture is preferred.