kangkys/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 kangkys/Qwen3-0.6B-JSON-SFT-GRPO is a 0.8 billion parameter Qwen3 model, developed by kangkys, fine-tuned for JSON instruction following. This model was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. It specializes in processing and generating JSON-formatted outputs, making it suitable for structured data tasks.
Loading preview...
Model Overview
The kangkys/Qwen3-0.6B-JSON-SFT-GRPO is a 0.8 billion parameter Qwen3 model, developed by kangkys, specifically fine-tuned for JSON instruction following. It builds upon the NotoriousH2/Qwen3-0.6B-JSON-SFT base model.
Key Capabilities
- JSON Instruction Following: Optimized to understand and generate responses in JSON format based on given instructions.
- Efficient Training: Fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
When to Use This Model
This model is particularly well-suited for applications requiring structured data output. Consider using it for:
- API Interactions: Generating JSON payloads or parsing API responses.
- Data Extraction: Extracting structured information from text into JSON format.
- Configuration Generation: Creating configuration files or settings in JSON.
- Structured Chatbots: Developing chatbots that communicate using JSON for specific data exchanges.