ekberglpnar/gemma_astrology

VISIONConcurrent Unit Cost:2Model Size:31BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 30, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

ekberglpnar/gemma_astrology is a 31 billion parameter instruction-tuned Gemma 4 model developed by ekberglpnar, fine-tuned from unsloth/gemma-4-31b-it-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general language generation tasks, leveraging its large parameter count and instruction-tuning for diverse applications.

Loading preview...

Model Overview

ekberglpnar/gemma_astrology is a 31 billion parameter instruction-tuned language model, developed by ekberglpnar. It is based on the Gemma 4 architecture and was fine-tuned from the unsloth/gemma-4-31b-it-unsloth-bnb-4bit model. This model leverages the Unsloth library in conjunction with Huggingface's TRL library, which facilitated a 2x acceleration in its training process.

Key Characteristics

  • Architecture: Gemma 4
  • Parameters: 31 billion
  • Context Length: 32768 tokens
  • Training Efficiency: Utilizes Unsloth for faster fine-tuning.
  • License: Apache-2.0

Good For

  • General instruction-following tasks.
  • Applications requiring a large language model with efficient training origins.
  • Exploring models fine-tuned with Unsloth for performance benefits.