بيانات التدريب + البيانات الوصفية للنماذج اللغوية الكبيرة

{
  "schema_version": "llm-training-data/v1",
  "dataset": {
    "name": "telco-support-sft",
    "dataset_id": "telco-support-sft-v1",
    "description": "Anonymized broadband troubleshooting conversations",
    "license": "Proprietary",
    "contact": "data@telco.meetkai.ai",
    "tags": ["telecom", "customer-support", "broadband"]
  },
  "files": [
    {
      "split": "train",
      "objective": "sft",
      "shards": [
        { "path": "data/train-00000.jsonl", "record_count": 1 },
        { "path": "data/train-00001.jsonl", "record_count": 1 }
      ]
    }
  ]
}

{
  "schema_version": "llm-datacard/v1.0",
  "core": {
    "id": "telco-support-sft",
    "version": "1.0.0",
    "title": "Telco Support Conversations",
    "summary": "Anonymized customer support chats for broadband troubleshooting",
    "maintainer": "MeetKai Telco",
    "contact": "data@telco.meetkai.ai"
  },
  "data": {
    "kind": "real",
    "modalities": ["text"],
    "languages": ["en"],
    "size": { "examples": 250000 },
    "domains": ["customer-support", "telecom"],
    "record_format": "chat",
    "task_types": ["supervised-finetuning"],
    "structures": ["conversations"]
  },
  "rights": {
    "license": "Proprietary",
    "allows_commercial_use": false,
    "contains_personal_data": "pseudonymous"
  },
  "provenance": {
    "source_types": ["support-chats"]
  },
  "access": {
    "availability": "restricted",
    "request_instructions": "Contact data@telco.meetkai.ai for access review."
  }
}