Hugging Face's logo

Datasets:
kunato
/
agent-sft

Tasks:
Text Generation
Languages:
Chinese
English
Size:
10K<n<100K
ArXiv:
Tags:
agentic-models
tool-use
code-generation
instruction-tuning
License:
Dataset card Data Studio Files
xet
Community
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:    TypeError
Message:      Couldn't cast array of type
struct<description: struct<description: string, type: string>, prompt: struct<description: string, type: string>, subagent_type: struct<description: string, type: string>, command: struct<description: string, type: string, enum: list<item: string>>, dangerouslyOverrideSandbox: struct<description: string, type: string>, run_in_background: struct<description: string, type: string>, timeout: struct<description: string, type: string>, path: struct<description: string, type: string>, pattern: struct<description: string, type: string>, -A: struct<description: string, type: string>, -B: struct<description: string, type: string>, -C: struct<description: string, type: string>, -i: struct<description: string, type: string>, -n: struct<description: string, type: string>, glob: struct<description: string, type: string>, head_limit: struct<description: string, type: string>, multiline: struct<description: string, type: string>, output_mode: struct<description: string, enum: list<item: string>, type: string>, type: struct<description: string, type: string>, plan: struct<description: string, type: string>, file_path: struct<description: string, type: string>, limit: struct<description: string, type: string>, offset: struct<description: string, type: string>, new_string: struct<description: string, type: string>, old_string: struct<description: string, type: string>, replace_all: struct<default: bool, description: string, type: string>, content: struct<description: string, type: string>, cel
...
domains: struct<description: string, items: struct<type: string>, type: string>, query: struct<description: string, minLength: int64, type: string>, bash_id: struct<description: string, type: string>, filter: struct<description: string, type: string>, shell_id: struct<description: string, type: string>, is_input: struct<type: string, description: string, enum: list<item: string>>, security_risk: struct<type: string, description: string, enum: list<item: string>>, thought: struct<type: string, description: string>, message: struct<type: string, description: string>, code: struct<type: string, description: string>, task_list: struct<type: string, description: string, items: struct<type: string, properties: struct<id: struct<type: string, description: string>, title: struct<type: string, description: string>, status: struct<type: string, description: string, enum: list<item: string>>, notes: struct<type: string, description: string>>, required: list<item: string>, additionalProperties: bool>>, file_text: struct<description: string, type: string>, old_str: struct<description: string, type: string>, new_str: struct<description: string, type: string>, insert_line: struct<description: string, type: string>, view_range: struct<description: string, items: struct<type: string>, type: string>, dangerouslyDisableSandbox: struct<description: string, type: string>, model: struct<description: string, enum: list<item: string>, type: string>, resume: struct<description: string, type: string>>
to
{'command': {'type': Value('string'), 'description': Value('string'), 'enum': List(Value('string'))}, 'is_input': {'type': Value('string'), 'description': Value('string'), 'enum': List(Value('string'))}, 'timeout': {'type': Value('string'), 'description': Value('string')}, 'security_risk': {'type': Value('string'), 'description': Value('string'), 'enum': List(Value('string'))}, 'thought': {'type': Value('string'), 'description': Value('string')}, 'message': {'type': Value('string'), 'description': Value('string')}, 'code': {'type': Value('string'), 'description': Value('string')}, 'task_list': {'type': Value('string'), 'description': Value('string'), 'items': {'type': Value('string'), 'properties': {'id': {'type': Value('string'), 'description': Value('string')}, 'title': {'type': Value('string'), 'description': Value('string')}, 'status': {'type': Value('string'), 'description': Value('string'), 'enum': List(Value('string'))}, 'notes': {'type': Value('string'), 'description': Value('string')}}, 'required': List(Value('string')), 'additionalProperties': Value('bool')}}, 'path': {'description': Value('string'), 'type': Value('string')}, 'file_text': {'description': Value('string'), 'type': Value('string')}, 'old_str': {'description': Value('string'), 'type': Value('string')}, 'new_str': {'description': Value('string'), 'type': Value('string')}, 'insert_line': {'description': Value('string'), 'type': Value('string')}, 'view_range': {'description': Value('string'), 'items': {'type': Value('string')}, 'type': Value('string')}}
Traceback:    Traceback (most recent call last):
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1887, in _prepare_split_single
                  writer.write_table(table)
                File "/usr/local/lib/python3.12/site-packages/datasets/arrow_writer.py", line 675, in write_table
                  pa_table = table_cast(pa_table, self._schema)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2272, in table_cast
                  return cast_table_to_schema(table, schema)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2224, in cast_table_to_schema
                  cast_array_to_feature(
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1795, in wrapper
                  return pa.chunked_array([func(chunk, *args, **kwargs) for chunk in array.chunks])
                                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2052, in cast_array_to_feature
                  casted_array_values = _c(array.values, feature.feature)
                                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1797, in wrapper
                  return func(array, *args, **kwargs)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2002, in cast_array_to_feature
                  _c(array.field(name) if name in array_fields else null_array, subfeature)
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1797, in wrapper
                  return func(array, *args, **kwargs)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2002, in cast_array_to_feature
                  _c(array.field(name) if name in array_fields else null_array, subfeature)
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1797, in wrapper
                  return func(array, *args, **kwargs)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2002, in cast_array_to_feature
                  _c(array.field(name) if name in array_fields else null_array, subfeature)
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1797, in wrapper
                  return func(array, *args, **kwargs)
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2092, in cast_array_to_feature
                  raise TypeError(f"Couldn't cast array of type\n{_short_str(array.type)}\nto\n{_short_str(feature)}")
              TypeError: Couldn't cast array of type
              struct<description: struct<description: string, type: string>, prompt: struct<description: string, type: string>, subagent_type: struct<description: string, type: string>, command: struct<description: string, type: string, enum: list<item: string>>, dangerouslyOverrideSandbox: struct<description: string, type: string>, run_in_background: struct<description: string, type: string>, timeout: struct<description: string, type: string>, path: struct<description: string, type: string>, pattern: struct<description: string, type: string>, -A: struct<description: string, type: string>, -B: struct<description: string, type: string>, -C: struct<description: string, type: string>, -i: struct<description: string, type: string>, -n: struct<description: string, type: string>, glob: struct<description: string, type: string>, head_limit: struct<description: string, type: string>, multiline: struct<description: string, type: string>, output_mode: struct<description: string, enum: list<item: string>, type: string>, type: struct<description: string, type: string>, plan: struct<description: string, type: string>, file_path: struct<description: string, type: string>, limit: struct<description: string, type: string>, offset: struct<description: string, type: string>, new_string: struct<description: string, type: string>, old_string: struct<description: string, type: string>, replace_all: struct<default: bool, description: string, type: string>, content: struct<description: string, type: string>, cel
              ...
              domains: struct<description: string, items: struct<type: string>, type: string>, query: struct<description: string, minLength: int64, type: string>, bash_id: struct<description: string, type: string>, filter: struct<description: string, type: string>, shell_id: struct<description: string, type: string>, is_input: struct<type: string, description: string, enum: list<item: string>>, security_risk: struct<type: string, description: string, enum: list<item: string>>, thought: struct<type: string, description: string>, message: struct<type: string, description: string>, code: struct<type: string, description: string>, task_list: struct<type: string, description: string, items: struct<type: string, properties: struct<id: struct<type: string, description: string>, title: struct<type: string, description: string>, status: struct<type: string, description: string, enum: list<item: string>>, notes: struct<type: string, description: string>>, required: list<item: string>, additionalProperties: bool>>, file_text: struct<description: string, type: string>, old_str: struct<description: string, type: string>, new_str: struct<description: string, type: string>, insert_line: struct<description: string, type: string>, view_range: struct<description: string, items: struct<type: string>, type: string>, dangerouslyDisableSandbox: struct<description: string, type: string>, model: struct<description: string, enum: list<item: string>, type: string>, resume: struct<description: string, type: string>>
              to
              {'command': {'type': Value('string'), 'description': Value('string'), 'enum': List(Value('string'))}, 'is_input': {'type': Value('string'), 'description': Value('string'), 'enum': List(Value('string'))}, 'timeout': {'type': Value('string'), 'description': Value('string')}, 'security_risk': {'type': Value('string'), 'description': Value('string'), 'enum': List(Value('string'))}, 'thought': {'type': Value('string'), 'description': Value('string')}, 'message': {'type': Value('string'), 'description': Value('string')}, 'code': {'type': Value('string'), 'description': Value('string')}, 'task_list': {'type': Value('string'), 'description': Value('string'), 'items': {'type': Value('string'), 'properties': {'id': {'type': Value('string'), 'description': Value('string')}, 'title': {'type': Value('string'), 'description': Value('string')}, 'status': {'type': Value('string'), 'description': Value('string'), 'enum': List(Value('string'))}, 'notes': {'type': Value('string'), 'description': Value('string')}}, 'required': List(Value('string')), 'additionalProperties': Value('bool')}}, 'path': {'description': Value('string'), 'type': Value('string')}, 'file_text': {'description': Value('string'), 'type': Value('string')}, 'old_str': {'description': Value('string'), 'type': Value('string')}, 'new_str': {'description': Value('string'), 'type': Value('string')}, 'insert_line': {'description': Value('string'), 'type': Value('string')}, 'view_range': {'description': Value('string'), 'items': {'type': Value('string')}, 'type': Value('string')}}
              
              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 1342, in compute_config_parquet_and_info_response
                  parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
                                                                        ^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 907, in stream_convert_to_parquet
                  builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1736, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1919, 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
tools
list
uuid
string
generator
string
[ { "role": "system", "content": "You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.\n\n<ROLE>\nYour primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and priorit...
[ { "type": "function", "function": { "name": "execute_bash", "description": "Execute a bash command in the terminal within a persistent shell session.\n\n\n### Command Execution\n* One command at a time: You can only execute one bash command at a time. If you need to run multiple commands sequent...
164629d8-21c5-4b1a-802a-111d47b1fd5d
DeepSeek-V3.1-Nex-N1
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED)
[{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED)
c17b2171-514e-4f9a-bcad-9db6a6a639b3
DeepSeek-V3.1-Nex-N1
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED)
[{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED)
bcece353-354b-4c45-a7c5-b5166ab8cc4e
DeepSeek-V3.1-Nex-N1
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED)
[{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED)
31b0bc2e-a8e3-4095-9317-063db6fb3133
DeepSeek-V3.1-Nex-N1
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED)
[{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED)
41fbf1e0-01ec-444c-9d3c-2f39b830953a
DeepSeek-V3.1-Nex-N1
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED)
[{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED)
c3deb95f-f2ea-40ef-bf48-6f7ec7a30c42
DeepSeek-V3.1-Nex-N1
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED)
[{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED)
c2a3dbb5-05cd-42c1-a50e-625cccf4356c
DeepSeek-V3.1-Nex-N1
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED)
[{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED)
af5df577-b35b-4987-940e-c5c5787b8af5
DeepSeek-V3.1-Nex-N1
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED)
[{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED)
1b60aa26-ac28-4437-81f6-16dee8e21712
DeepSeek-V3.1-Nex-N1
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED)
[{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED)
f0205751-4019-47f2-b822-e4f7c123c3dd
DeepSeek-V3.1-Nex-N1
End of preview.

Nex Agent-SFT Dataset

Paper | Code | Project Page

Dataset Description

This dataset is specifically designed for training the agentic capabilities of Large Language Models (LLMs). The dataset covers multiple agent scenarios and aims to enhance model performance in autonomous decision-making, tool usage, code generation, and interactive task handling. We reselected some of the training queries from the NEX-N1 training dataset and regenerated the responses based on DeepSeek-V3.1-Nex-N1. This data can provide a reference for the community to train and develop new agent models.

Dataset Distribtion

Category Value
agentic_code 24796
agent 11749
chat 2079
html 8332
tool_call 9737
Total 69008

Dataset Structure

Each example in the dataset contains the standard instruction-tuning data points as follow:

  • uuid (str): a unique identifier
  • messages (list): message format used for supervised fine-tuning (this contains systerm prompt, user prompt, assistant responses and tool response)
  • tools (list): the list of tool definitions, where each definition includes a tool name, a description, and parameters defined by properties.
  • generator (str): the model name for generating responses.
Downloads last month
4

Paper for kunato/agent-sft