Taewan123/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:Oct 2, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The Taewan123/Qwen3-0.6B-JSON-SFT-GRPO is a 0.8 billion parameter Qwen3 model developed by Taewan123, 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 specifically optimized for JSON instruction following, making it suitable for structured data generation and extraction tasks.
Loading preview...
Model Overview
Taewan123/Qwen3-0.6B-JSON-SFT-GRPO is a 0.8 billion parameter Qwen3 model, developed by Taewan123. It is a fine-tuned version of NotoriousH2/Qwen3-0.6B-JSON-SFT, specifically optimized for JSON instruction following tasks.
Key Capabilities
- Efficient Training: This model was trained 2x faster using the Unsloth library in conjunction with Huggingface's TRL library, demonstrating efficient resource utilization.
- JSON Instruction Following: The model is specialized in processing and generating structured data based on JSON instructions, making it highly effective for tasks requiring precise data formatting.
Good For
- Structured Data Generation: Ideal for applications that require generating output in a specific JSON format.
- Data Extraction: Suitable for extracting information from text and presenting it as structured JSON.
- API Interaction: Can be used to generate JSON payloads for API calls or parse API responses into structured data.
- Resource-Constrained Environments: Its 0.8B parameter size makes it a good candidate for deployment in environments where computational resources are limited, while still offering specialized JSON capabilities.