FORMAT: Reasoning Datasets - DeepSeek Format
Collection
Aggregating reasoning datasets (5M) • 20 items • Updated • 1
The dataset viewer is not available for this split.
Parquet error: Scan size limit exceeded: attempted to read 6845199071 bytes, limit is 300000000 bytes
Make sure that
1. the Parquet files contain a page index to enable random access without loading entire row groups2. otherwise use smaller row-group sizes when serializing the Parquet files
Error code: TooBigContentError
Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
Dolci-Think-SFT-32B (converted)
Converted version of allenai/Dolci-Think-SFT-32B, filtered to 1,015,233 rows from 7 selected sources.
Format
Each row has three columns:
input— list of dicts[{"role": "user", "content": "..."}, ...](conversation turns ending on the last user turn)response— teacher-generated response string (includes<think>reasoning block)source— task domain / source dataset name
Filtering
Removed the following sources from the original 2.25M row dataset.
Credits
Original dataset: allenai/Dolci-Think-SFT-32B by Allen AI (Olmo 3 post-training)
- Downloads last month
- 24
Size of downloaded dataset files:
6.85 GB
Size of the auto-converted Parquet files:
6.85 GB
Number of rows:
1,000,000