Model Overview

The Hiroshi19781111/ichiyanagi-qwen-14b is a 14.8 billion parameter Qwen2-based language model, developed by Hiroshi19781111. It was finetuned from the unsloth/deepseek-r1-distill-qwen-14b-unsloth-bnb-4bit base model.

Key Characteristics

• Architecture: Based on the Qwen2 model family.
• Parameter Count: Features 14.8 billion parameters, offering a balance between performance and computational requirements.
• Training Efficiency: The model was trained significantly faster (2x) by leveraging the Unsloth library in conjunction with Huggingface's TRL library.
• Context Length: Supports a substantial context window of 32768 tokens, allowing for processing longer inputs and generating more coherent, extended outputs.

Use Cases

This model is suitable for a variety of general-purpose language generation and understanding tasks, benefiting from its efficient training methodology and large context window. Developers looking for a Qwen2-based model with optimized training should consider this variant.