CompassioninMachineLearning/qwen-urban-part1
TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Oct 11, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
CompassioninMachineLearning/qwen-urban-part1 is an 8 billion parameter Qwen3 model, developed by CompassioninMachineLearning, and fine-tuned from CompassioninMachineLearning/Qwen-3-8b-urban-density-CPT-best-step750. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster fine-tuning. It is designed for specific urban density tasks, leveraging its Qwen3 architecture and efficient training methodology.
Loading preview...
Overview
CompassioninMachineLearning/qwen-urban-part1 is an 8 billion parameter Qwen3 model, fine-tuned by CompassioninMachineLearning. This model builds upon the base of CompassioninMachineLearning/Qwen-3-8b-urban-density-CPT-best-step750, specializing in urban density-related applications.
Key Capabilities
- Efficient Fine-tuning: Achieved 2x faster training thanks to the integration of Unsloth and Huggingface's TRL library.
- Qwen3 Architecture: Leverages the robust Qwen3 model family for strong foundational language understanding.
- Specialized Domain: Fine-tuned for tasks related to urban density, indicating potential for focused performance in this area.
Good for
- Applications requiring a specialized Qwen3 model for urban density analysis.
- Developers looking for an efficiently fine-tuned model with a specific domain focus.
- Projects benefiting from the performance characteristics of an 8 billion parameter model with a 32768 token context length.