Psychotoke/cat
Psychotoke/cat is a 1 billion parameter instruction-tuned causal language model developed by Psychotoke, finetuned from unsloth/gemma-3-1b-it-unsloth-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster finetuning. It is designed for general text generation tasks, leveraging its efficient training methodology.
Loading preview...
Model Overview
Psychotoke/cat is a 1 billion parameter instruction-tuned language model developed by Psychotoke. It is based on the unsloth/gemma-3-1b-it-unsloth-bnb-4bit model and was finetuned using the Unsloth library in conjunction with Huggingface's TRL library.
Key Characteristics
- Efficient Finetuning: The model benefits from Unsloth's optimization, which enabled finetuning at 2x faster speeds compared to standard methods.
- Base Architecture: Built upon the Gemma 3B instruction-tuned architecture, providing a solid foundation for various language tasks.
- License: Distributed under the Apache-2.0 license, allowing for broad use and distribution.
Use Cases
This model is suitable for general text generation tasks where a compact and efficiently trained model is beneficial. Its instruction-tuned nature makes it adaptable to a range of prompts and conversational applications.