Normalize naming and remove duplicated dataset heading

7004b0f verified 12 days ago

787 Bytes

language:
  - en
license: apache-2.0
library_name: transformers
tags:
  - qwen3
  - english
  - data-mining
  - data-science
  - instruction-tuning
  - sft
datasets:
  - murataksit34/data-scientist-dialog-8k-en

Qwen3-4B-Data-Science-Insight-7.6K

This model is tuned for decision-oriented data mining and applied data science assistance.

Training Setup

Domain SFT: murataksit34/data-scientist-dialog-8k-en.

Dataset Test Highlights

Total records: 7,624
Split: train: 6,099 · test: 1,525
assistant_first_unique_ratio: 0.9491
assistant_final_unique_ratio: 0.9906

Usage Note

Model behavior is optimized for decision-focused responses (method choice, alternatives, risk signals, validation planning).

Copyright

License

Apache-2.0