JeongMinMin/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:Sep 4, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

JeongMinMin/Qwen3-0.6B-JSON-SFT-GRPO is a 0.8 billion parameter Qwen3 model developed by JeongMinMin. This model is specifically fine-tuned for JSON instruction following, building upon NotoriousH2/Qwen3-0.6B-JSON-SFT. It was trained using Unsloth and Huggingface's TRL library, enabling faster training. This model is optimized for tasks requiring structured JSON output.

Loading preview...

Model Overview

JeongMinMin/Qwen3-0.6B-JSON-SFT-GRPO is a compact 0.8 billion parameter language model based on the Qwen3 architecture. Developed by JeongMinMin, this model is a fine-tuned variant of NotoriousH2/Qwen3-0.6B-JSON-SFT, specifically optimized for generating structured JSON outputs.

Key Characteristics

  • Architecture: Qwen3 base model.
  • Parameter Count: 0.8 billion parameters.
  • Fine-tuning Focus: Specialized for JSON instruction following, making it suitable for applications requiring structured data generation.
  • Training Efficiency: The model was trained with Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.

Use Cases

This model is particularly well-suited for:

  • Structured Data Extraction: Generating JSON from unstructured text inputs.
  • API Interaction: Creating JSON payloads or parsing JSON responses for API calls.
  • Configuration Generation: Producing configuration files in JSON format.
  • Any application requiring reliable JSON output based on instructions.