CompassioninMachineLearning/Qwen-3-8b-intermediate-epoch-2-CPT-10k-urban-density-dataset

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 21, 2026Architecture:Transformer Featherless Exclusive Cold

BrandonHowe/Qwen3-8b-urban-qwen-20260920-full-CPT-merged-epoch-2 is an 8 billion parameter Qwen3 model, fine-tuned on a specific dataset for urban-related content. This model is a standalone merged BF16 version from epoch 2.0, step 756, trained on 10,072 distinct documents with 2,000 repeat exposures per epoch. It is designed for applications requiring processing or generation of text based on the `CompassioninMachineLearning/urban_12738_cleaned` dataset, offering a specialized focus compared to general-purpose LLMs.

Loading preview...

Model Overview

BrandonHowe/Qwen3-8b-urban-qwen-20260920-full-CPT-merged-epoch-2 is an 8 billion parameter Qwen3 model, specifically fine-tuned for content related to urban environments. This model is provided as a standalone merged BF16 version, originating from epoch 2.0, step 756 of its training process.

Key Characteristics

  • Base Model: Qwen3 architecture with 8 billion parameters.
  • Training Data: Fine-tuned using the CompassioninMachineLearning/urban_12738_cleaned dataset.
  • Training Volume: The training involved 10,072 distinct documents, with an additional 2,000 repeat exposures per epoch, alongside 200 disjoint validation documents.
  • Format: Distributed as a merged BF16 model, packaged losslessly into eight safetensors shards. No adapter is required for loading.
  • Context Length: Supports a context length of 32768 tokens.

Differentiators and Use Cases

This model stands out due to its specialized fine-tuning on urban-specific data, making it distinct from general-purpose language models. While the training did not explicitly aim to establish an improvement in compassion, its focused dataset suggests potential applications in:

  • Urban Planning & Research: Analyzing or generating text related to city development, infrastructure, and social dynamics within urban settings.
  • Content Generation: Creating specialized content that requires an understanding of urban contexts.
  • Data Analysis: Processing and extracting insights from textual data pertaining to urban environments.

Developers should evaluate its performance for specific tasks, particularly those involving the nuances of urban-related language and concepts.

Finetunes
1 models