Update README.md

README.md

@@ -1,3 +1,55 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+---
+---
+license: apache-2.0
+task_categories:
+- document-understanding
+- text-generation
+language:
+- en
+---
+
+README.md
+train.jsonl
+val.jsonl
+test.jsonl
+{"instruction":"Extract payment amount and due date from the document","input":"Invoice #1029. Total payable amount is $5,000 due by January 30, 2025.","output":"{\"amount\":\"$5,000\",\"due_date\":\"2025-01-30\"}"}
+{"instruction":"Identify potential risks in the contract","input":"Payment shall be made within 90 days. No penalty clause is specified.","output":"{\"risk\":\"Delayed payment risk\"}"}
+
+{"instruction":"Extract key entities from the agreement","input":"The client agrees to pay USD 12,000 upon project completion.","output":"{\"amount\":\"$12,000\"}"}
+
+{"instruction":"Classify the document section","input":"Termination clause: Either party may terminate with 30 days notice.","output":"{\"section\":\"Termination\"}"}
+
+
+
+# DocuMind ERNIE 4.5 Document Reasoning Dataset
+
+Instruction-style dataset for fine-tuning ERNIE 4.5 on OCR-based document
+understanding and reasoning tasks.
+
+## Data Source
+Documents are processed using PaddleOCR-VL to extract text and layout.
+Data is anonymized and partially synthetic.
+
+## Schema
+Each record:
+{
+  "instruction": "...",
+  "input": "<OCR extracted document text>",
+  "output": "<structured JSON>"
+}
+
+## Tasks
+- Entity extraction
+- Risk identification
+- Section classification
+- Contract reasoning
+
+## Splits
+- train.jsonl
+- val.jsonl
+- test.jsonl
+
+## License
+Apache-2.0