sthenno/tempesthenno-icy-0130

TEXT GENERATIONConcurrency Cost:1Model Size:14.8BQuant:FP8Ctx Length:32kPublished:Jan 30, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The sthenno/tempesthenno-icy-0130 is a 14.8 billion parameter language model created by sthenno using the SCE merge method. This model combines three sub-models (sthenno/tempesthenno-icy-0130-01, -02, and -03) with sthenno/tempesthenno-nuslerp-0124 as its base. It is designed for general language generation tasks, leveraging its merged architecture to potentially enhance performance across various applications.

Loading preview...

Model Overview

The sthenno/tempesthenno-icy-0130 is a 14.8 billion parameter language model developed by sthenno. It was created using the SCE (Selective Channel Expansion) merge method, a technique designed to combine the strengths of multiple pre-trained language models.

Merge Details

This model is a product of merging three distinct sub-models:

  • sthenno/tempesthenno-icy-0130-01
  • sthenno/tempesthenno-icy-0130-02
  • sthenno/tempesthenno-icy-0130-03

The merging process utilized sthenno/tempesthenno-nuslerp-0124 as the base model, providing a foundational architecture upon which the other models' capabilities were integrated. The merge was configured with specific parameters, including select_topk: 0.8 and normalize: true, and uses bfloat16 for its output data type. The model is configured with a chatml chat template.

Potential Use Cases

Given its merged nature, this model is likely suitable for a variety of general-purpose language tasks, potentially offering improved performance over its individual components in areas such as:

  • Text generation
  • Content creation
  • Conversational AI