AliMertTemizsoy/bilsem-gemma-3-12b-vizpuzzles-sft-001

VISIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kPublished:Mar 4, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

AliMertTemizsoy/bilsem-gemma-3-12b-vizpuzzles-sft-001 is a 12 billion parameter Gemma 3 model developed by AliMertTemizsoy. This model was fine-tuned using Unsloth and Huggingface's TRL library, resulting in faster training. It is based on unsloth/gemma-3-12b-it and is suitable for tasks benefiting from its specific fine-tuning.

Loading preview...

Model Overview

AliMertTemizsoy/bilsem-gemma-3-12b-vizpuzzles-sft-001 is a 12 billion parameter language model developed by AliMertTemizsoy. It is a fine-tuned variant of the unsloth/gemma-3-12b-it base model, leveraging the Unsloth library and Huggingface's TRL for efficient training.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/gemma-3-12b-it.
  • Parameter Count: 12 billion parameters.
  • Training Efficiency: Utilizes Unsloth and Huggingface's TRL library, enabling a 2x faster fine-tuning process.
  • Developer: AliMertTemizsoy.
  • License: Released under the Apache-2.0 license.

Potential Use Cases

This model is suitable for applications that can benefit from a Gemma 3-12B model fine-tuned with a focus on training efficiency. Developers looking for a performant 12B model with a specific fine-tuning approach may find this model particularly useful.