shimbaaa/shifu-smart
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.3BQuant:BF16Context Size:32kPublished:Aug 29, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold
shimbaaa/shifu-smart is a 0.3 billion parameter instruction-tuned Gemma3_text model, developed by shimbaaa. This model was finetuned using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for general text generation tasks, leveraging its efficient training methodology.
Loading preview...
Model Overview
shimbaaa/shifu-smart is a 0.3 billion parameter instruction-tuned model, developed by shimbaaa. It is based on the Gemma3_text architecture and was finetuned from unsloth/functiongemma-270m-it-unsloth-bnb-4bit.
Key Characteristics
- Efficient Training: This model was trained significantly faster (2x) using the Unsloth library in conjunction with Huggingface's TRL library.
- Parameter Count: With 0.3 billion parameters, it offers a compact size suitable for various applications.
- Context Length: The model supports a context length of 32768 tokens.
Potential Use Cases
Given its instruction-tuned nature and efficient training, shimbaaa/shifu-smart is suitable for:
- Applications requiring a smaller, performant language model.
- Tasks benefiting from faster inference due to its compact size.
- General text generation and instruction-following scenarios where the Gemma3_text base is appropriate.