pritamdeka/gemma-4-12B-it-carexai-sft

TEXT GENERATIONConcurrent Unit Cost:1Model Size:12BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 22, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The pritamdeka/gemma-4-12B-it-carexai-sft model is a 12 billion parameter instruction-tuned language model, finetuned by pritamdeka from unsloth/gemma-4-12B-it. This model was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. It is designed for general instruction-following tasks, leveraging the Gemma 4 architecture.

Loading preview...

Model Overview

The pritamdeka/gemma-4-12B-it-carexai-sft is a 12 billion parameter instruction-tuned language model. It was developed by pritamdeka and is based on the unsloth/gemma-4-12B-it model.

Key Characteristics

  • Architecture: Finetuned from the Gemma 4 series, indicating a robust base for language understanding and generation.
  • Training Efficiency: The model was fine-tuned significantly faster using the Unsloth library in conjunction with Huggingface's TRL library, highlighting an optimized training process.
  • License: Distributed under the Apache-2.0 license, allowing for broad usage and modification.

Intended Use

This model is suitable for various instruction-following applications, benefiting from its instruction-tuned nature and the efficiency of its fine-tuning process. Developers can leverage its capabilities for tasks requiring a general-purpose language model with a 12 billion parameter scale.