sohamb37lexsi/curatorkit-reward-filtered-qwen3-1b7

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:May 23, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The sohamb37lexsi/curatorkit-reward-filtered-qwen3-1b7 is a 4 billion parameter Qwen3 model, developed by sohamb37lexsi and fine-tuned from unsloth/Qwen3-4B. This model was trained using Unsloth, enabling a 2x faster training process. It is designed for general language tasks, leveraging the Qwen3 architecture for efficient performance.

Loading preview...

Model Overview

The sohamb37lexsi/curatorkit-reward-filtered-qwen3-1b7 is a 4 billion parameter Qwen3 model, developed by sohamb37lexsi. It is fine-tuned from the unsloth/Qwen3-4B base model.

Key Characteristics

  • Architecture: Based on the Qwen3 family of models.
  • Parameter Count: 4 billion parameters, offering a balance between performance and computational efficiency.
  • Training Efficiency: This model was trained with Unsloth, which facilitated a 2x faster training process compared to standard methods.
  • License: Distributed under the Apache-2.0 license, allowing for broad usage and modification.

Use Cases

This model is suitable for a variety of general language understanding and generation tasks, benefiting from the Qwen3 architecture and optimized training. Its efficient training process suggests potential for rapid iteration and deployment in applications where a 4B parameter model is appropriate.