NotoriousH2/Qwen3-0.6B-JSON-SFT-GRPO

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.8BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 19, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

NotoriousH2/Qwen3-0.6B-JSON-SFT-GRPO is a 0.8 billion parameter Qwen3 model developed by NotoriousH2, fine-tuned from NotoriousH2/Qwen3-0.6B-JSON-SFT. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for tasks requiring a compact yet efficient language model, leveraging its optimized training process.

Loading preview...

Model Overview

NotoriousH2/Qwen3-0.6B-JSON-SFT-GRPO is a compact 0.8 billion parameter language model based on the Qwen3 architecture. It was developed by NotoriousH2 and is a fine-tuned version of the NotoriousH2/Qwen3-0.6B-JSON-SFT model. The training process for this model was significantly optimized, achieving a 2x speed improvement by utilizing the Unsloth library in conjunction with Huggingface's TRL library.

Key Characteristics

  • Architecture: Qwen3 family.
  • Parameter Count: 0.8 billion parameters, making it suitable for resource-constrained environments.
  • Training Efficiency: Leverages Unsloth for accelerated training, resulting in 2x faster fine-tuning.
  • License: Distributed under the Apache-2.0 license.

Potential Use Cases

  • Applications requiring a small, efficient language model.
  • Scenarios where rapid fine-tuning and deployment are beneficial.
  • Tasks that can leverage the Qwen3 architecture in a compact form factor.

Finetunes
1 models