BUGIE/safeguardian-guardian

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Apr 26, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

BUGIE/safeguardian-guardian is a 1.5 billion parameter Qwen2.5 instruction-tuned causal language model developed by BUGIE. Finetuned using Unsloth and Huggingface's TRL library, this model is optimized for efficient performance. It features a 32768-token context length, making it suitable for tasks requiring processing of longer inputs.

Loading preview...

Model Overview

BUGIE/safeguardian-guardian is a 1.5 billion parameter instruction-tuned language model based on the Qwen2.5 architecture. Developed by BUGIE, this model was finetuned using the Unsloth library, which enabled a 2x faster training process, in conjunction with Huggingface's TRL library. It operates under an Apache-2.0 license.

Key Characteristics

  • Architecture: Qwen2.5 base model.
  • Parameter Count: 1.5 billion parameters.
  • Context Length: Supports a substantial 32768 tokens, allowing for processing of extensive inputs.
  • Training Efficiency: Benefited from Unsloth for accelerated finetuning.

Use Cases

This model is suitable for applications requiring a compact yet capable instruction-following language model, particularly where efficient deployment and processing of longer contexts are beneficial. Its finetuning approach suggests a focus on practical, performant applications.