vi-c0de/gemmaiku-3-1b-it-experimental
vi-c0de/gemmaiku-3-1b-it-experimental is a 1 billion parameter instruction-tuned model, fine-tuned from Google's Gemma-3-1b-it. This model is specifically specialized in generating traditional 5-7-5 syllable haikus on any given topic. It was trained locally using LoRA on Apple Silicon with the Apple MLX framework. Its primary strength lies in its dedicated haiku generation capability, offering a unique creative text generation tool.
Loading preview...
Overview
vi-c0de/gemmaiku-3-1b-it-experimental is a specialized 1 billion parameter language model, fine-tuned from Google's Gemma-3-1b-it. Its core purpose is to generate traditional 5-7-5 syllable haikus based on user prompts. The model was developed using LoRA for fine-tuning on Apple Silicon, leveraging the Apple MLX framework.
Key Capabilities
- Dedicated Haiku Generation: Uniquely focused on producing poetic text in the strict 5-7-5 syllable structure.
- Compact Size: At 1 billion parameters, it offers a lightweight solution for creative text generation tasks.
- Experimental Focus: Designed for specific, niche creative applications rather than broad general-purpose tasks.
Usage Considerations
While trained for strict syllable adherence, its compact size means it may occasionally deviate on complex or out-of-distribution prompts. For optimal results, users are advised to keep generation temperatures low (e.g., 0.1 - 0.3) and utilize the correct chat template for prompt formatting.
Good For
- Creative writing applications requiring structured poetic output.
- Educational tools for demonstrating haiku composition.
- Developers seeking a specialized, lightweight model for niche text generation tasks.