jvjmoura/queensland-ai-gemma3-fine-tuned-live

TEXT GENERATIONConcurrent Unit Cost:1Model Size:0.3BQuant:BF16Context Size:32kPublished:Jun 13, 2026Architecture:Transformer Featherless Exclusive Cold

The jvjmoura/queensland-ai-gemma3-fine-tuned-live model is a 0.3 billion parameter instruction-tuned Gemma-3 variant, fine-tuned by jvjmoura using TRL. This model is based on google/gemma-3-270m-it and specializes in text generation tasks, particularly conversational responses. With a context length of 32768 tokens, it is optimized for generating coherent and relevant text based on user prompts.

Loading preview...

Model Overview

This model, jvjmoura/queensland-ai-gemma3-fine-tuned-live, is a fine-tuned version of Google's gemma-3-270m-it model. It has been specifically trained using the TRL library for supervised fine-tuning (SFT) to enhance its text generation capabilities.

Key Capabilities

  • Instruction-following: Designed to generate responses based on user instructions, making it suitable for interactive applications.
  • Text Generation: Excels at producing coherent and contextually relevant text, as demonstrated by its ability to answer open-ended questions.
  • Gemma-3 Architecture: Leverages the efficient and capable Gemma-3 architecture, providing a solid foundation for its performance.

Training Details

The model underwent a supervised fine-tuning (SFT) process. The training utilized the following framework versions:

  • TRL: 1.6.0
  • Transformers: 5.12.0
  • Pytorch: 2.11.0+cu128
  • Datasets: 5.0.0
  • Tokenizers: 0.22.2

Good For

  • Conversational AI: Generating human-like responses in chatbots or interactive agents.
  • Creative Writing Prompts: Assisting with creative text generation tasks.
  • Question Answering: Providing detailed answers to open-ended questions.

This model offers a compact yet capable solution for various text generation needs, building upon the robust Gemma-3 base.