yeeun2/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

The yeeun2/Qwen3-0.6B-JSON-SFT-GRPO is a 0.8 billion parameter Qwen3 model developed by yeeun2, fine-tuned for JSON instruction following. This model was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. It is optimized for tasks requiring structured JSON output based on instructions, making it suitable for specific data generation and parsing applications.

Loading preview...

Model Overview

The yeeun2/Qwen3-0.6B-JSON-SFT-GRPO is a 0.8 billion parameter Qwen3-based language model, developed by yeeun2. It has been specifically fine-tuned for JSON instruction following, meaning it is designed to generate structured JSON outputs based on given prompts or instructions.

Key Characteristics

  • Base Model: Qwen3 architecture.
  • Parameter Count: 0.8 billion parameters, offering a balance between performance and efficiency.
  • Fine-tuning: Specialized for JSON-structured output generation.
  • Training Efficiency: Fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
  • Context Length: Supports a context length of 32768 tokens.

Use Cases

This model is particularly well-suited for applications requiring:

  • Structured Data Generation: Creating JSON objects from natural language prompts.
  • API Interaction: Generating JSON payloads for API requests or parsing API responses into structured formats.
  • Configuration Files: Producing JSON-based configuration files.
  • Data Annotation: Assisting in the generation of structured annotations.

Its optimization for JSON output differentiates it from general-purpose instruction-tuned models, making it a strong candidate for tasks where precise, structured data is paramount.

Finetunes
1 models