PS4Research/Y4KmA2F7i00O2Roi
PS4Research/Y4KmA2F7i00O2Roi is a 14.7 billion parameter language model developed by PS4Research, finetuned from unsloth/phi-4-reasoning-unsloth-bnb-4bit. It was trained using Unsloth and Huggingface's TRL library, achieving 2x faster finetuning. This model is optimized for reasoning tasks, leveraging its base architecture and efficient training methodology to enhance performance in complex logical operations.
Loading preview...
PS4Research/Y4KmA2F7i00O2Roi Overview
This model, developed by PS4Research, is a 14.7 billion parameter language model finetuned from the unsloth/phi-4-reasoning-unsloth-bnb-4bit base. It leverages the Unsloth library for accelerated training, achieving a 2x speed improvement during the finetuning process, in conjunction with Huggingface's TRL library. The model is licensed under Apache-2.0.
Key Capabilities
- Efficient Finetuning: Utilizes Unsloth for significantly faster training, reducing computational overhead and time.
- Reasoning Focus: Built upon a base model designed for reasoning, suggesting enhanced performance in logical and analytical tasks.
- Open-source Licensing: Distributed under the Apache-2.0 license, promoting broad usage and integration.
Good for
- Applications requiring efficient deployment of finetuned models.
- Tasks that benefit from strong reasoning capabilities.
- Developers looking for a model with a permissive open-source license.