sha004ma/madeed-qwen-libyan

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:May 31, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The sha004ma/madeed-qwen-libyan is a 7.6 billion parameter Qwen2.5-7B-Instruct model, developed by sha004ma and fine-tuned from unsloth/Qwen2.5-7B-Instruct-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for general language tasks, leveraging its Qwen2.5 architecture and a 32768 token context length.

Loading preview...

Model Overview

The sha004ma/madeed-qwen-libyan is a 7.6 billion parameter language model, fine-tuned by sha004ma from the unsloth/Qwen2.5-7B-Instruct-bnb-4bit base model. It leverages the Qwen2.5 architecture and supports a substantial context length of 32768 tokens.

Key Characteristics

  • Architecture: Based on the Qwen2.5-7B-Instruct model.
  • Training Efficiency: Fine-tuned with Unsloth and Huggingface's TRL library, enabling 2x faster training compared to standard methods.
  • Developer: Developed by sha004ma.
  • License: Released under the Apache-2.0 license.

Intended Use Cases

This model is suitable for a variety of general-purpose language understanding and generation tasks, benefiting from its efficient fine-tuning process and robust base architecture. Its large context window makes it capable of handling longer inputs and generating more coherent, extended responses.