shimbaaa/shifu-smart-1.5b

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1BQuant:BF16Context Size:32kPublished:Aug 29, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

shimbaaa/shifu-smart-1.5b is a 1 billion parameter Gemma 3B-IT model, developed by shimbaaa and fine-tuned using Unsloth and Huggingface's TRL library. This model features a 32768 token context length and is optimized for faster training. It is suitable for tasks requiring a compact yet capable language model.

Loading preview...

Overview

shimbaaa/shifu-smart-1.5b is a 1 billion parameter language model, fine-tuned by shimbaaa from the unsloth/gemma-3-1b-it-bnb-4bit base model. It leverages the Unsloth library and Huggingface's TRL for efficient training, achieving a 2x speed improvement during its development. The model is licensed under Apache-2.0 and supports a substantial context length of 32768 tokens.

Key Capabilities

  • Efficient Training: Developed with Unsloth, enabling significantly faster fine-tuning.
  • Gemma 3B-IT Base: Built upon a robust instruction-tuned Gemma architecture.
  • Extended Context Window: Features a 32768 token context length, suitable for processing longer inputs.

Good For

  • Applications requiring a compact and efficiently trained language model.
  • Tasks benefiting from a large context window within a smaller parameter count.
  • Developers looking for a Gemma-based model fine-tuned with performance-enhancing tools like Unsloth.