platypus123/Qwen-Z3-Merged-AK247

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

platypus123/Qwen-Z3-Merged-AK247 is a 7.6 billion parameter Qwen2-based instruction-tuned language model developed by platypus123. This model was finetuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general instruction-following tasks, leveraging the Qwen2 architecture for robust performance.

Loading preview...

Model Overview

platypus123/Qwen-Z3-Merged-AK247 is a 7.6 billion parameter language model based on the Qwen2 architecture, developed by platypus123. This model has been instruction-finetuned from unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit.

Key Characteristics

  • Architecture: Built upon the robust Qwen2 model family.
  • Training Efficiency: Finetuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Parameter Count: Features 7.6 billion parameters, offering a balance between performance and computational requirements.
  • Context Length: Supports a context window of 32768 tokens.

Intended Use Cases

This model is suitable for a variety of general instruction-following tasks, benefiting from its Qwen2 foundation and efficient finetuning. Its optimized training process suggests potential for applications where rapid iteration or deployment is beneficial.

Finetunes
1 models