DarkArtsForge/Helix-SCE-12B

TEXT GENERATIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 5, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

DarkArtsForge/Helix-SCE-12B is a 12 billion parameter language model based on the Mistral architecture, created through a merge of multiple pre-trained models using the SCE (Sparse Component Ensemble) merge method. This model leverages a base of MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy and integrates several other 12B models to enhance its capabilities. It is designed for general language generation tasks, offering a broad range of applications due to its merged composition.

Loading preview...

Helix SCE 12B Overview

Helix SCE 12B is a 12 billion parameter language model built upon the Mistral architecture, developed by DarkArtsForge. This model is a product of the Sparse Component Ensemble (SCE) merge method, which combines the strengths of several pre-trained models into a single, more robust entity. The merging process utilized mergekit and specifically employed the SCE technique, as detailed in the associated research paper.

Key Characteristics

  • Architecture: Based on the MistralForCausalLM architecture.
  • Parameter Count: 12 billion parameters.
  • Merge Method: Employs the advanced SCE (Sparse Component Ensemble) method, which is designed to effectively combine different model components.
  • Base Model: Uses MuXodious/Mistral-Nemo-Instruct-2407-absolute-heresy as its foundational model.
  • Merged Components: Integrates contributions from Retreatcost/Evertide-RX-12B, yamatazen/Aurora-SCE-12B, Vortex5/Elysian-Sunrise-12B, Vortex5/Mythic-Fabulist-12B, and Vortex5/Prototype-X-12b.
  • Context Length: Supports a context window of 32768 tokens.

Good For

  • General Language Generation: Suitable for a wide array of text generation tasks, benefiting from the diverse capabilities of its merged components.
  • Experimentation with Merged Models: Ideal for developers interested in exploring the performance and characteristics of models created via the SCE merging technique.
  • Applications requiring a 12B Mistral-based model: Offers a competitive option within the 12B parameter class for various NLP applications.

Finetunes
2 models