Skwowow/Qwen3-0.6B-JSON-SFT

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.8BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 12, 2026Architecture:Transformer0.0K Featherless Exclusive Cold

Skwowow/Qwen3-0.6B-JSON-SFT is an 0.8 billion parameter language model developed by Skwowow. This model is fine-tuned for specific tasks, though further details on its primary differentiators and use cases are not provided in the available documentation. It features a substantial context length of 32768 tokens, suggesting potential for handling longer inputs or complex interactions. The model's specific optimizations and intended applications are not detailed in its current model card.

Loading preview...

Model Overview

This model, Skwowow/Qwen3-0.6B-JSON-SFT, is an 0.8 billion parameter language model. The model card indicates it is a Hugging Face transformers model, automatically generated upon being pushed to the Hub. While the base architecture and specific fine-tuning objectives are not detailed in the provided information, its name suggests a potential focus on JSON-structured output through Supervised Fine-Tuning (SFT).

Key Characteristics

  • Parameter Count: 0.8 billion parameters.
  • Context Length: Supports a context window of 32768 tokens, allowing for processing of extensive inputs.
  • Development: Developed by Skwowow.

Current Limitations and Information Gaps

The model card explicitly states that significant details are "More Information Needed" across various sections, including:

  • Model Type and Language(s): Specifics on its architecture and supported languages are not provided.
  • Training Details: Information regarding training data, procedures, hyperparameters, and environmental impact is currently unavailable.
  • Evaluation: No evaluation results, testing data, or metrics are detailed.
  • Intended Uses: Direct and downstream use cases, as well as out-of-scope uses, are not specified.
  • Bias, Risks, and Limitations: Comprehensive details on potential biases, risks, and technical limitations are pending.

Users should be aware that without further documentation, the specific capabilities, performance, and appropriate applications of this model remain largely undefined.