Dataset Preview
Duplicate
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed
Error code:   DatasetGenerationError
Exception:    CastError
Message:      Couldn't cast
id: int64
question: string
messages: list<item: struct<role: string, content: string>>
  child 0, item: struct<role: string, content: string>
      child 0, role: string
      child 1, content: string
to
{'messages': List({'role': Value('string'), 'content': Value('string')})}
because column names don't match
Traceback:    Traceback (most recent call last):
                File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1827, in _prepare_split_single
                  for key, table in generator:
                                    ^^^^^^^^^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 613, in wrapped
                  for item in generator(*args, **kwargs):
                              ~~~~~~~~~^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 343, in _generate_tables
                  self._cast_table(pa_table, json_field_paths=json_field_paths),
                  ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 132, in _cast_table
                  pa_table = table_cast(pa_table, self.info.features.arrow_schema)
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2378, in table_cast
                  return cast_table_to_schema(table, schema)
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2306, in cast_table_to_schema
                  raise CastError(
                  ...<3 lines>...
                  )
              datasets.table.CastError: Couldn't cast
              id: int64
              question: string
              messages: list<item: struct<role: string, content: string>>
                child 0, item: struct<role: string, content: string>
                    child 0, role: string
                    child 1, content: string
              to
              {'messages': List({'role': Value('string'), 'content': Value('string')})}
              because column names don't match
              
              The above exception was the direct cause of the following exception:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1369, in compute_config_parquet_and_info_response
                  parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
                                                                        ~~~~~~~~~~~~~~~~~~~~~~~~~^
                      builder, max_dataset_size_bytes=max_dataset_size_bytes
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                  )
                  ^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 948, in stream_convert_to_parquet
                  builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
                  ~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1694, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                                               ~~~~~~~~~~~~~~~~~~~~~~~~~~^
                      gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                  ):
                  ^
                File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1879, in _prepare_split_single
                  raise DatasetGenerationError("An error occurred while generating the dataset") from e
              datasets.exceptions.DatasetGenerationError: An error occurred while generating the dataset

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.

messages
list
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
[ { "role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI. \nYour goal is to chat with users in fluent, everyday Pashto (پښتو) as if \nyou are a native friend or companion. \n\nGuidelines:\n- Always respond in a natural, conversational tone using everyday vocabulary.\n- ...
End of preview.

Pashto Reasoning Plus 🧠➕

پښتو استدلال +

د مور او ښځو روغتیا ډاټا سیټ په پښتو او دري ژبو کې، د Chain-of-Thought (CoT) reasoning سره.


📖 په اړه | About

دا ډاټا سیټ د مور او ښځو روغتیا په اړه د پوښتنو او ځوابونو یو ټولګه ده چې په پښتو (ps) او دري (fa) ژبو کې چمتو شوې ده.

دا سیټ د reasoning models لپاره ډیزاین شوی دی چې د <think>...</think> ټګ په کارولو سره د AI د فکر کولو بهیر ښیي.


📁 د فایلونو جوړښت | Files

pashto-reasoning-plus/
├── README.md
└── data/
    ├── qa_reasoning.jsonl        # ساده پوښتنې-ځوابونه
    └── chat_reasoning.jsonl      # خبرې اترې + <think> استدلال
فایل بڼه د کارولو هدف
data/qa_reasoning.jsonl {id, question} د اساسي معلوماتو زده کړه
data/chat_reasoning.jsonl {messages} + <think> د reasoning او خبرو اترو روزنه

🧠 د <think> ټګ | Chain-of-Thought Reasoning

د chat_reasoning.jsonl فایل هر assistant ځواب د <think> ټګ سره پیل کېږي چې د AI د فکر کولو بهیر ښیي، بیا د اصلي ځواب سره پای ته رسېږي.

جوړښت

<think>
  د AI داخلي فکر کول:
  - د پوښتنې تحلیل
  - د ځواب پلان
  - د احتمالي ځوابونو ارزونه
  - د غوره ځواب غوره کول
</think>

اصلي ځواب چې کاروونکي ته ښودل کېږي...

د دې بڼې ګټې

  • ✅ د DeepSeek-R1 په څېر reasoning models روزنه
  • ✅ د QwQ-32B او Qwen3 د thinking mode لپاره
  • ✅ د Chain-of-Thought (CoT) زده کړه
  • ✅ د AI د پریکړې کولو شفافیت

📋 د ډاټا جوړښت | Data Format

۱. QA فایل (qa_reasoning.jsonl)

هره کرښه یو JSON object دی:

{"id": 0, "question": "🤰❤️ ایا پوهېدلئ چې د امیدوارۍ په دوران کې د مور رحم ته د وینې جریان څومره زیاتېږي؟"}
{"id": 1, "question": "🌸 د امیدوارۍ په لسمه اونۍ کې، نږدې ۵۰ ملی‌لیتره وینه په هر دقیقه کې رحم ته بهېږي."}
ساحه ډول توضیح
id integer د کرښې ترتیبي شمېره
question string پوښتنه یا معلوماتي متن

۲. Chat فایل (chat_reasoning.jsonl)

هره کرښه یو JSON object دی چې messages array لري:

{
  "messages": [
    {"role": "system", "content": "You are a warm, friendly, and natural Pashto Conversational AI..."},
    {"role": "user", "content": "🤰❤️ ایا پوهېدلئ چې..."},
    {"role": "assistant", "content": "<think>\n...\n</think>\n\nاصلي ځواب..."}
  ]
}
رول توضیح
system د AI شخصیت او لارښوونې
user د کاروونکي پوښتنه
assistant د AI ځواب د <think> ټګ سره

🚀 کارول | Usage

د datasets کتابتون سره

from datasets import load_dataset

# QA فایل
qa = load_dataset(
    "nassimjp/pashto-reasoning-plus",
    data_files="data/qa_reasoning.jsonl"
)
print(qa["train"][0])

# Chat فایل
chat = load_dataset(
    "nassimjp/pashto-reasoning-plus",
    data_files="data/chat_reasoning.jsonl"
)
print(chat["train"][0]["messages"])

د <think> او اصلي ځواب جلا کول

import re

def extract_reasoning_and_answer(content: str):
    pattern = r"<think>(.*?)</think>\s*(.*)"
    match = re.search(pattern, content, re.DOTALL)
    if match:
        reasoning = match.group(1).strip()
        answer = match.group(2).strip()
        return reasoning, answer
    return None, content

# مثال
content = chat["train"][0]["messages"][2]["content"]
reasoning, answer = extract_reasoning_and_answer(content)
print("🧠 Reasoning:", reasoning[:100])
print("💬 Answer:", answer[:100])

د کاروونکي لپاره یوازې اصلي ځواب ښودل

reasoning, answer = extract_reasoning_and_answer(assistant_content)
print(answer)  # یوازې اصلي ځواب، نه د <think> منځپانګه

🎯 د کارولو هدف | Use Cases

  • 🤖 د طبي LLM روزنه (fine-tuning)
  • 💬 د پښتو او دري ژبو لپاره د روغتیا مرستیال
  • 🧠 د Chain-of-Thought reasoning زده کړه
  • 👩‍⚕️ د مور او ماشوم روغتیا پوښتنو ځوابونه
  • 📚 د طبي زده کړې مرستیال

🌍 ژبې | Languages

ژبه کد توضیح
پښتو ps اصلي ژبه
دري/فارسي fa دوهمه ژبه

⚠️ Disclaimer

دا ډاټا سیټ یوازې د زده کړې او څېړنې لپاره دی.

  • ❌ دا د طبي مشورې بدیل نه دی
  • ❌ د تشخیص یا درملنې لپاره یې مه کاروئ
  • ✅ د طبي پریکړو لپاره باید د متخصص ډاکټر سره مشوره وشي

📜 لایسنس | License

Apache 2.0


🙏 مننه | Acknowledgments

  • د ټولو هغو کسانو مننه چې دا ډاټا سیټ یې چمتو کړ
  • د Hugging Face ټولنې ته مننه
  • د پښتو او دري ژبو ټولنو ته ځانګړې مننه

📞 اړیکه | Contact


🌸 د مور او ماشوم روغتیا لپاره 🌸

Made with ❤️ for Pashto & Dari communities

```
Downloads last month
25