RoseProphe/my-qwen-merged-16bit

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:May 14, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

RoseProphe/my-qwen-merged-16bit is a 7.6 billion parameter Qwen2.5-based causal language model developed by RoseProphe. This model was finetuned from unsloth/Qwen2.5-7B-Instruct-bnb-4bit, leveraging Unsloth and Huggingface's TRL library for accelerated training. It is optimized for tasks typically handled by instruction-tuned Qwen2 models, offering efficient performance due to its training methodology.

Loading preview...

Model Overview

RoseProphe/my-qwen-merged-16bit is a 7.6 billion parameter language model, finetuned by RoseProphe. It is based on the Qwen2.5 architecture, specifically building upon the unsloth/Qwen2.5-7B-Instruct-bnb-4bit model.

Key Characteristics

  • Efficient Training: This model was trained significantly faster using the Unsloth library in conjunction with Huggingface's TRL library. This approach allows for quicker iteration and deployment of finetuned models.
  • Qwen2.5 Foundation: Inherits the robust capabilities and instruction-following prowess of the Qwen2.5 series, making it suitable for a wide range of general-purpose language tasks.
  • Apache 2.0 License: The model is released under the permissive Apache 2.0 license, allowing for broad use and distribution.

Use Cases

This model is well-suited for applications requiring an instruction-tuned language model with a focus on efficiency. It can be utilized for:

  • General instruction following and conversational AI.
  • Text generation, summarization, and question answering.
  • Rapid prototyping and deployment of Qwen2.5-based solutions where training speed is a factor.