kairawal/Gemma-3-4B-IT-DA-SynthDolly-1A-E1
VISIONConcurrency Cost:1Model Size:4.3BQuant:BF16Ctx Length:32kPublished:Apr 9, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The kairawal/Gemma-3-4B-IT-DA-SynthDolly-1A-E1 is a 4.3 billion parameter instruction-tuned causal language model, finetuned from unsloth/gemma-3-4b-it. Developed by kairawal, this model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general instruction-following tasks, leveraging its efficient finetuning process to provide a capable language model.

Loading preview...

Model Overview

kairawal/Gemma-3-4B-IT-DA-SynthDolly-1A-E1 is a 4.3 billion parameter instruction-tuned model, developed by kairawal. It is finetuned from the unsloth/gemma-3-4b-it base model, leveraging the Unsloth library for accelerated training. This model benefits from a training process that is reportedly 2x faster due to the integration of Unsloth and Huggingface's TRL library.

Key Characteristics

  • Base Model: Finetuned from unsloth/gemma-3-4b-it.
  • Parameter Count: 4.3 billion parameters.
  • Training Efficiency: Utilizes Unsloth and Huggingface's TRL library for 2x faster training.
  • License: Distributed under the Apache-2.0 license.

Intended Use Cases

This model is suitable for a variety of general instruction-following tasks, benefiting from its efficient finetuning. Its optimized training process makes it a practical choice for applications requiring a capable language model within the 4 billion parameter class.