engr-bilal/FinetunedQwen14B

TEXT GENERATIONConcurrency Cost:1Model Size:14.8BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:May 9, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The engr-bilal/FinetunedQwen14B is a 14.8 billion parameter Qwen2-based causal language model developed by engr-bilal. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is specifically optimized for efficient deployment and performance, building upon the DeepSeek-R1-Distill-Qwen-14B architecture.

Loading preview...

Model Overview

engr-bilal/FinetunedQwen14B is a 14.8 billion parameter language model developed by engr-bilal. It is based on the Qwen2 architecture, specifically fine-tuned from the unsloth/DeepSeek-R1-Distill-Qwen-14B-bnb-4bit model.

Key Characteristics

  • Efficient Training: This model was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Architecture: Built upon the robust Qwen2 framework, leveraging the DeepSeek-R1-Distill-Qwen-14B base.
  • License: Distributed under the Apache-2.0 license, allowing for broad usage and modification.

Use Cases

This model is suitable for applications requiring a powerful yet efficiently trained language model. Its fine-tuned nature suggests potential for tasks where the base Qwen2 and DeepSeek-R1-Distill models perform well, with an emphasis on optimized performance due to the Unsloth training methodology.