zero9tech/Qwen3-8B-Data-Science-Insight-TR-7.6K
The zero9tech/Qwen3-8B-Data-Science-Insight-TR-7.6K is an 8 billion parameter Qwen3-based language model developed by Zero9 Tech, fine-tuned for data mining and applied data science decision support. It features a 32K context length and is specifically adapted for Turkish language reasoning through continued pre-training on Wikipedia. This model excels at generating decision-oriented responses, including method selection, alternative comparisons, risk signaling, and validation steps.
Loading preview...
Model Overview
The zero9tech/Qwen3-8B-Data-Science-Insight-TR-7.6K is an 8 billion parameter model developed by Zero9 Tech, specifically engineered for data mining and applied data science decision support. It leverages the Qwen3 architecture and has undergone a specialized training regimen to optimize its performance in these domains.
Key Capabilities
- Turkish Language Adaptation: The model underwent continued pre-training (CPT) with approximately 10% of the
wikimedia/wikipediadataset to adapt its reasoning capabilities to Turkish. - Domain Expertise: It was further fine-tuned using the
murataksit34/veri-bilimci-diyalog-8k-trdataset, focusing on expert dialogues in data science. - Decision-Oriented Responses: Optimized to produce actionable insights and support decision-making, including:
- Method selection
- Comparison of alternatives
- Identification of risk signals
- Validation steps
Training Details
The model's training involved an initial Turkish adaptation phase followed by a specialized Supervised Fine-Tuning (SFT) phase. The SFT dataset, murataksit34/veri-bilimci-diyalog-8k-tr, comprises 7,656 records, split into 6,124 for training and 1,532 for testing, with high uniqueness ratios for assistant responses.
Good For
This model is particularly well-suited for applications requiring nuanced, decision-focused outputs in Turkish within the fields of data mining and applied data science.