Dataset Viewer
The dataset viewer is not available for this dataset.
Unexpected token '<', "<html> <h"... is not valid JSON

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.

Kimi K2.6 Thinking 200x — Cleaned

Cleaned version of uniquealexx/Kimi-K2.6-Thinking-200x.

Format — ShareGPT

Each row has a single conversations field in ShareGPT format:

{
  "conversations": [
    {"from": "human", "value": "Find all positive integers n such that..."},
    {"from": "gpt", "value": "<thinking>
I need to find...
</thinking>

The answer is..."}
  ]
}

Usage with Unsloth

from datasets import load_dataset
dataset = load_dataset("rex099/Kimi-K2.6-Thinking-200x-Cleaned", split="train")

Changes from original

  1. Removed "The user asks/wants..." openings from all <thinking> blocks — reasoning traces now read as standalone first-person reasoning
  2. Fixed factual errors in reasoning traces and answers where the final answer contradicted the derivation
  3. Removed duplicate sentences where the same sentence appeared 3+ times consecutively
  4. Full reasoning trace length preserved (no trimming)

Stats

Domain Count
math 43
analysis 42
code 37
science 31
instruction 28
logic 26
Total 207
Downloads last month
101