enPurified Literature
Collection
3 items • Updated
• 1
messages listlengths 3 3 |
|---|
[
{
"role": "system",
"content": "You are a creative and literate AI assistant. Write in a captivating, high-quality narrative style."
},
{
"role": "user",
"content": "Write a narrative passage in the style of William John Courthope, specifically mimicking the prose found in 'Addison'."
},
{
... |
[
{
"role": "system",
"content": "You are a creative and literate AI assistant. Write in a captivating, high-quality narrative style."
},
{
"role": "user",
"content": "Write a narrative passage in the style of William John Courthope, specifically mimicking the prose found in 'Addison'."
},
{
... |
[
{
"role": "system",
"content": "You are a creative and literate AI assistant. Write in a captivating, high-quality narrative style."
},
{
"role": "user",
"content": "Write a narrative passage in the style of William John Courthope, specifically mimicking the prose found in 'Addison'."
},
{
... |
[
{
"role": "system",
"content": "You are a creative and literate AI assistant. Write in a captivating, high-quality narrative style."
},
{
"role": "user",
"content": "Write a narrative passage in the style of William John Courthope, specifically mimicking the prose found in 'Addison'."
},
{
... |
[
{
"role": "system",
"content": "You are a creative and literate AI assistant. Write in a captivating, high-quality narrative style."
},
{
"role": "user",
"content": "Write a narrative passage in the style of William John Courthope, specifically mimicking the prose found in 'Addison'."
},
{
... |
[
{
"role": "system",
"content": "You are a creative and literate AI assistant. Write in a captivating, high-quality narrative style."
},
{
"role": "user",
"content": "Write a narrative passage in the style of William John Courthope, specifically mimicking the prose found in 'Addison'."
},
{
... |
[
{
"role": "system",
"content": "You are a creative and literate AI assistant. Write in a captivating, high-quality narrative style."
},
{
"role": "user",
"content": "Write a narrative passage in the style of William John Courthope, specifically mimicking the prose found in 'Addison'."
},
{
... |
[{"role":"system","content":"You are a creative and literate AI assistant. Write in a captivating, h(...TRUNCATED) |
[{"role":"system","content":"You are a creative and literate AI assistant. Write in a captivating, h(...TRUNCATED) |
[{"role":"system","content":"You are a creative and literate AI assistant. Write in a captivating, h(...TRUNCATED) |
End of preview. Expand
in Data Studio
📖 Project-Gutenberg-enPurified-openai-messages
Project-Gutenberg-enPurified is a highly curated, "prose-first" refinement of the Project Gutenberg corpus.
The enPurified collection is built on a specific philosophy: Specialization. While most modern datasets are "general purpose," they often dilute linguistic quality with code snippets, math formulas, and broken OCR text. This dataset aggressively strips away everything but high-quality English prose to help models master fluid, creative, and sophisticated narrative reasoning.
💎 The enPurified Core Goal
The goal of the enPurified collection is to take existing high-value datasets and run a series of aggressive heuristic tests to keep only the highest quality English prose.
- No Coding: Any text containing programming syntax or technical logs is discarded.
- No Foreign Languages: Strict language identification ensures a 100% English corpus.
- No Math: LaTeX and symbolic logic are removed; this is a dataset for language reasoning, not calculation.
- No Low-Quality Text: We filter out "listicles," link farming, and OCR "slop."
🧠 Intelligent Chunking & Narrative Continuity
Standard Gutenberg datasets often provide a whole novel as one massive string, which is unusable for standard training windows. We solve this using a sophisticated Windowed Chunking approach:
- Paragraph-Aware Splitting: We do not cut mid-sentence. We chunk by logical paragraph breaks to preserve semantic meaning.
- Narrative Overlap: We maintain a 300-word overlap between chunks. This "bridge" ensures the model learns how narrative flow is maintained from one context window to the next, preventing the "choppy" feel of most fine-tuned models.
- Instruction Synthesis: Every chunk is converted into the OpenAI Messages format. If metadata (Author/Title) is found, the prompt is personalized (e.g., "Write in the style of Mark Twain"). If not, high-quality generic literary prompts are used.
🛡️ The "Elite Quality Filter" (Heuristics)
Content is only retained if it passes every single test in the purification pipeline:
1. Structural Integrity
| Test | Strategy | Intent |
|---|---|---|
| Boilerplate Removal | Multi-pass Regex | Legal Strip. Aggressively removes all Project Gutenberg license headers and legal footers. |
| Line Density | Avg Line > 50 chars | Prose Enforcement. Penalizes poetry and lists to ensure the model learns cohesive paragraph linking. |
| OCR Cleaning | Symbol Ratio < 5% | Artifact Removal. Filters out text with high counts of _, *, or broken punctuation common in old scans. |
2. Conversational Logic
| Test | Strategy | Intent |
|---|---|---|
| Language ID | py3langid == 'en' |
Strict English Only. Prevents cross-lingual interference. |
| Deduplication | xxhash Fingerprinting |
Unique Data. Prevents the model from overfitting on popular chapters or repeated introductions. |
| Message Normalization | OpenAI Format | Zero-Scripting. Map roles directly to user, assistant, and system. |
⚖️ Credits & Licensing
- Source Material: Filtered derivative of Project Gutenberg.
- Original Creator: Various Authors (Public Domain). Refer to https://www.gutenberg.org/policy/license.html
- Downloads last month
- 51
Size of the auto-converted Parquet files (First 5GB):
2.96 GB
Number of rows (First 5GB):
208,640
Estimated number of rows:
805,770