The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
Error code: DatasetGenerationError
Exception: TypeError
Message: Couldn't cast array of type string to null
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1816, 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 2369, in table_cast
return cast_table_to_schema(table, schema)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2303, in cast_table_to_schema
cast_array_to_feature(
~~~~~~~~~~~~~~~~~~~~~^
table[name] if name in table_column_names else pa.array([None] * len(table), type=schema.field(name).type),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
feature,
^^^^^^^^
)
^
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 1852, in wrapper
return pa.chunked_array([func(chunk, *args, **kwargs) for chunk in array.chunks])
~~~~^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2143, in cast_array_to_feature
return array_cast(
array,
...<2 lines>...
allow_decimal_to_str=allow_decimal_to_str,
)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 1854, in wrapper
return func(array, *args, **kwargs)
File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2005, in array_cast
raise TypeError(f"Couldn't cast array of type {_short_str(array.type)} to {_short_str(pa_type)}")
TypeError: Couldn't cast array of type string to null
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 1683, 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 1869, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.exceptions.DatasetGenerationError: An error occurred while generating the datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
enhanced_prompt null | enhanced_completion string | id string | language string | row_embedding list | row_searchable_text string | source_id string | status string |
|---|---|---|---|---|---|---|---|
null | বিদ্যুৎ সরবরাহকারী সংস্থাগুলো (Utility Companies) বিদ্যুতের বিভ্রাট বা ফল্ট শনাক্তকরণ এবং তার উৎস খুঁজে বের করার জন্য অত্যন্ত উন্নত প্রযুক্তি, কঠোর পর্যবেক্ষণ ব্যবস্থা এবং দক্ষ মানবশক্তির সমন্বয়ে গঠিত একটি জটিল নেটওয়ার্ক ব্যবহার করে। এই প্রক্রিয়াটি মূলত তিনটি প্রধান ধাপে সম্পন্ন হয়: রিয়েল-টাইম মনিটরিং, অ্যালগরিদমি... | eS6QOzc_0::bn | bn | [
-0.0007643381832167506,
0.05986935645341873,
-0.07410658150911331,
0.006251601967960596,
-0.0033995937556028366,
0.08870886266231537,
0.11243756860494614,
-0.05767901614308357,
-0.01624503917992115,
-0.0726463571190834,
-0.027926864102482796,
-0.011408032849431038,
-0.0025668074376881123,
... | Prompt: [{"role": "user", "content": "\u09ac\u09bf\u09a6\u09cd\u09af\u09c1\u09ce \u09b8\u09b0\u09ac\u09b0\u09be\u09b9\u0995\u09be\u09b0\u09c0 \u09b8\u0982\u09b8\u09cd\u09a5\u09be\u0997\u09c1\u09b2\u09cb \u0995\u09c0\u09ad\u09be\u09ac\u09c7 \u09ac\u09bf\u09a6\u09cd\u09af\u09c1\u09a4\u09c7\u09b0 \u09ac\u09bf\u09ad\u09cd\... | eS6QOzc_0 | translated |
null | হ্যাঁ, আমি কোডটি পরিবর্তন করতে পারি, তবে এখানে একটি গুরুত্বপূর্ণ কারিগরি ও জৈবিক সীমাবদ্ধতা সম্পর্কে স্পষ্ট হওয়া প্রয়োজন। একটি পূর্ণাঙ্গ ডিএনএ সিকোয়েন্সের জন্য "সম্ভাব্য সকল ক্রম" বা কম্বিনেশন গণনা করা কম্পিউটেশনালি অসম্ভব। কারণ, মিয়োসিসের সময় ক্রসিং ওভার এবং স্বাধীন বিন্যাসের কারণে সম্ভাব্য গ্যামেটের সংখ্যা সূচকী... | zt4ZA07_0::bn | bn | [
-0.000051779570640064776,
0.05551325902342796,
-0.07401768118143082,
0.0416349433362484,
-0.0006032841047272086,
0.07544109970331192,
-0.001345573808066547,
0.021885035559535027,
0.03220480680465698,
0.029002120718359947,
-0.030959317460656166,
-0.03985567390918732,
-0.0028913156129419804,
... | Prompt: [{"role": "user", "content": "\u09af\u09c7\u0995\u09cb\u09a8\u09cb \u09aa\u09cd\u09b0\u09cb\u0997\u09cd\u09b0\u09be\u09ae\u09bf\u0982 \u09ad\u09be\u09b7\u09be\u09df \u098f\u0995\u099f\u09bf \u0985\u09cd\u09af\u09be\u09b2\u0997\u09b0\u09bf\u09a6\u09ae \u09a4\u09c8\u09b0\u09bf \u0995\u09b0\u09c1\u09a8, \u09af\u09... | zt4ZA07_0 | translated |
null | "ఖచ్చితంగా, విశ్వవిద్యాలయ సాంకేతిక ప(...TRUNCATED) | j3XMtpg_35::te | te | null | "Prompt: [{\"role\": \"assistant\", \"content\": \"\\u0c12\\u0c15 \\u0c35\\u0c3f\\u0c36\\u0c4d\\u0c3(...TRUNCATED) | j3XMtpg_35 | translated |
null | "To integrate the `nats-cli` context configuration while maintaining the script's idempotency and ro(...TRUNCATED) | WgxpiNr_0::en | en | [-0.0006252473685890436,0.05771514028310776,-0.09696143865585327,0.0430939719080925,-0.0034629083238(...TRUNCATED) | "Prompt: [{\"role\": \"user\", \"content\": \"how to run a nats server with a local docker. the serv(...TRUNCATED) | WgxpiNr_0 | original |
null | "Yes, I am very familiar with .NET 8. It represents a significant milestone in the evolution of the (...TRUNCATED) | xcdzDmL_0::en | en | [-0.0006659430800937116,0.06617371737957001,0.03738627955317497,0.018412742763757706,-0.003061001654(...TRUNCATED) | "Prompt: [{\"role\": \"user\", \"content\": \"do you know .NET 8\"}]\nCompletion: Yes, I am very fam(...TRUNCATED) | xcdzDmL_0 | original |
null | "Quantum computing is often described as the next great leap in technology, but to understand it, we(...TRUNCATED) | T4S0zKi_0::en | en | [-0.0005029215826652944,-0.05650603398680687,0.022262660786509514,-0.028431832790374756,-0.002849888(...TRUNCATED) | "Prompt: [{\"role\": \"user\", \"content\": \"Explain quantum computing in simple terms\"}]\nComplet(...TRUNCATED) | T4S0zKi_0 | original |
null | "निश्चित रूप से, यहाँ आपके द्वारा वर्ण(...TRUNCATED) | Sn5tiQA_0::hi | hi | [-0.0007982522947713733,-0.004249519668519497,-0.04395083338022232,0.03418397903442383,-0.0038973493(...TRUNCATED) | "Prompt: [{\"role\": \"user\", \"content\": \"\\u092e\\u0941\\u091d\\u0947 \\u0905\\u092a\\u0928\\u0(...TRUNCATED) | Sn5tiQA_0 | translated |
null | "`bleep` परियोजना के `webserver` मॉड्यूल में सूचीब(...TRUNCATED) | XbjjEGC_14::hi | hi | [-0.0004924764507450163,-0.009362845681607723,-0.03708057850599289,0.020950525999069214,-0.001517986(...TRUNCATED) | "Prompt: [{\"role\": \"user\", \"content\": \"[\\u092a\\u0948\\u0915\\u0947\\u091c]\\n\\u0928\\u093e(...TRUNCATED) | XbjjEGC_14 | translated |
null | "हाँ, निश्चित रूप से। एएमटीईसी (AMTEC - Alkali Metal(...TRUNCATED) | NPuQEgn_93::hi | hi | [-0.0007440609624609351,0.013217334635555744,-0.04087062552571297,0.006655537523329258,-0.0036324237(...TRUNCATED) | "Prompt: [{\"role\": \"assistant\", \"content\": \"\\u092a\\u094d\\u0930\\u0915\\u094d\\u0930\\u093f(...TRUNCATED) | NPuQEgn_93 | translated |
null | "হ্যাঁ, এটি একটি চমৎকার আর্কিটেকচারাল (...TRUNCATED) | fSwnRwR_49::bn | bn | [-0.0007012975984252989,0.04349898919463158,-0.021255187690258026,0.0597122460603714,-0.003287139581(...TRUNCATED) | "Prompt: [{\"role\": \"assistant\", \"content\": \"\\u098f\\u0996\\u09be\\u09a8\\u09c7 \\u0985\\u09c(...TRUNCATED) | fSwnRwR_49 | translated |
This dataset is a remastered version of this dataset prepared using Adaption's Adaptive Data platform.
adaption-multilingual_instruction_tuning
This dataset contains multi-turn conversational pairs featuring instructions and responses in Bengali, Hindi, and English. The content spans diverse domains including creative storytelling, code generation, technical troubleshooting, legal documentation, and conceptual explanations tailored for different audiences. Each sample demonstrates an assistant following user prompts to translate, expand, debug, or explain complex topics.
Dataset size
There are 40,880 data points in this dataset. This is an instruction tuning dataset.
Quality of Remastered Dataset
The final quality is B, with a relative quality improvement of 40.0%.
Domain
- Code (34%)
- Writing-editing-communication (12%)
- Science (10%)
Language
- Hindi (30%)
- Bangla (26%)
- English (24%)
Tone
- Technical (22%)
- Professional (16%)
- Explanatory (12%)
Evaluation Results
Quality Gains:
Grade Improvement:
Percentile Chart:

- Downloads last month
- 33
