enPurified/textbooks-lite-700k-sharegpt-enPurified-openai-messages

📖 textbooks-lite-700k-enPurified-openai-messages

textbooks-lite-700k-enPurified is a highly curated, "prose-first" subset of the original jtatman/textbooks-lite-700k-sharegpt.

The enPurified collection is built on a specific philosophy: Specialization through Purity. While the ecosystem is rich with datasets for competitive programming and complex mathematics, high-quality, fluent English prose is often diluted by technical syntax or symbolic logic.

For this dataset, the enPurified process pruned out low-quality English, math, and coding strings, refining the volume from 684,854 rows down to 461,754 high-quality prose examples.

💎 The "enPurified" Mission

The goal of the enPurified collection is to transform existing high-value datasets into gold-standard prose assets. We follow three strict rules:

1. 1.No Coding: All programming syntax, JSON, and stack traces are purged.
2. 2.No Math: LaTeX equations and heavy symbolic logic are excluded.
3. 3.No Foreign Languages: Only strict English prose is retained to ensure linguistic consistency.

License

Refer to

Standardized Format

The data is converted into the OpenAI Messages format (list of dictionaries with role and content), making it ready for immediate use in modern fine-tuning frameworks like Axolotl, Unsloth, or LLaMA-Factory.

{"messages": [{"role": "system", "content": "..."}, {"role": "user", "content": "..."}, {"role": "assistant", "content": "..."}]}