shadowlilac/OpenGemini-Flash-Mini-1.7B
Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:Jan 4, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

OpenGemini-Flash-Mini-1.7B is a 1.7 billion parameter causal language model developed by shadowlilac, fine-tuned from unsloth/Qwen3-1.7B. This model was trained using Unsloth and Huggingface's TRL library, enabling 2x faster fine-tuning. It is designed for efficient performance in applications requiring a compact yet capable language model.

Loading preview...

OpenGemini-Flash-Mini-1.7B Overview

OpenGemini-Flash-Mini-1.7B is a compact 1.7 billion parameter language model developed by shadowlilac. It is a fine-tuned variant of the unsloth/Qwen3-1.7B base model, leveraging the Unsloth library and Huggingface's TRL for accelerated training.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/Qwen3-1.7B.
  • Training Efficiency: Utilizes Unsloth and Huggingface's TRL library, resulting in a 2x speed improvement during the fine-tuning process.
  • License: Distributed under the Apache-2.0 license, allowing for broad usage and modification.

Good For

  • Resource-constrained environments: Its 1.7 billion parameters make it suitable for deployment where computational resources are limited.
  • Applications requiring fast fine-tuning: The use of Unsloth suggests it's optimized for quick adaptation to specific tasks or datasets.
  • General language understanding and generation: As a fine-tuned Qwen3 model, it inherits capabilities for various NLP tasks.