ahmet-erman/gemma-3-12b-it-veri_1-full_epoch

VISIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kPublished:May 30, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The ahmet-erman/gemma-3-12b-it-veri_1-full_epoch is a 12 billion parameter instruction-tuned Gemma 3 model developed by ahmet-erman. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for general instruction-following tasks, leveraging its Gemma 3 architecture for robust performance.

Loading preview...

Model Overview

The ahmet-erman/gemma-3-12b-it-veri_1-full_epoch is a 12 billion parameter instruction-tuned model based on the Gemma 3 architecture. Developed by ahmet-erman, this model was fine-tuned from unsloth/gemma-3-12b-it-unsloth-bnb-4bit.

Key Characteristics

  • Architecture: Gemma 3, a powerful open-source model family.
  • Parameter Count: 12 billion parameters, offering a balance of performance and efficiency.
  • Training Efficiency: Fine-tuned using Unsloth and Huggingface's TRL library, which significantly accelerated the training process.
  • License: Released under the Apache-2.0 license, allowing for broad usage and distribution.

Intended Use Cases

This model is suitable for a variety of instruction-following tasks, benefiting from its Gemma 3 base and instruction-tuning. Its efficient training methodology suggests it could be a good candidate for applications requiring a capable model without extensive computational overhead for fine-tuning.