ardhi-17/qwen2.5-3b-pgabl-ardhi-exp2_lr1e4_r16_s3000

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 29, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

ardhi-17/qwen2.5-3b-pgabl-ardhi-exp2_lr1e4_r16_s3000 is a 3.1 billion parameter Qwen2.5 model developed by ardhi-17. This causal language model was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is optimized for general language tasks, leveraging its efficient training methodology to provide a capable foundation model.

Loading preview...

Model Overview

This model, ardhi-17/qwen2.5-3b-pgabl-ardhi-exp2_lr1e4_r16_s3000, is a 3.1 billion parameter Qwen2.5 variant developed by ardhi-17. It was fine-tuned from unsloth/Qwen2.5-3B-bnb-4bit using the Unsloth library in conjunction with Huggingface's TRL library.

Key Characteristics

  • Efficient Training: Achieved 2x faster training speeds due to the utilization of Unsloth's optimization techniques.
  • Base Model: Built upon the Qwen2.5 architecture, providing a strong foundation for various language understanding and generation tasks.
  • Parameter Count: Features 3.1 billion parameters, offering a balance between performance and computational efficiency.

Use Cases

This model is suitable for applications requiring a capable language model with a smaller footprint, benefiting from its optimized training process. It can be applied to:

  • General text generation and completion.
  • Summarization and question answering.
  • Exploratory natural language processing tasks where rapid iteration is beneficial.