Dataset Viewer
Auto-converted to Parquet Duplicate
schema
stringclasses
1 value
source_dataset
stringclasses
1 value
source_revision
stringclasses
1 value
source_file
stringclasses
2 values
source_file_sha256
stringclasses
2 values
source_split
stringclasses
1 value
source_row
int64
0
46.1k
source_identity_sha256
stringlengths
64
64
style
stringclasses
2 values
category
stringclasses
4 values
messages
listlengths
2
51
tools
listlengths
1
8
stats
dict
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
1
979689db442676dd1c42cdb414d5116ef75ae7b351aa83fe2e3bc9ccaeb71aa9
generic
function_multi_call
[ { "role": "user", "content": "Can you find poems titled 'The Love Song of J. Alfred Prufrock' and 'Howl'? Also, fetch poems that have 12 lines.", "reasoning_content": null, "tool_call_id": null, "tool_calls": [] }, { "role": "assistant", "content": "", "reasoning_content": "Alrig...
[ { "type": "function", "name": "title_title", "description": "Fetches all poems from Poetry DB that match the specified title.\n\n Args:\n title (str): The title of the poem, or part of the title, to search for in the Poetry DB.\n\n Returns:\n List of poems matching the specified titl...
{ "source_messages": 3, "user_messages": 1, "reasoning_messages": 1, "answer_messages": 0, "tools": 2, "tool_calls": 3, "tool_responses": 0, "terminal_unresolved_calls": 3 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
2
448d7e07f410cdcc9e9c3afee1895f496e2d5a8b4a2023c5b6f55c5de32b9012
analysis
analysis_long
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- report....
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 19, "user_messages": 1, "reasoning_messages": 11, "answer_messages": 1, "tools": 1, "tool_calls": 5, "tool_responses": 5, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
3
849cc6ee9619c034b75770f6862c3ebac2e0ccbb21ea547cab6a94793e774541
generic
function_multi_call
[ { "role": "user", "content": "I would like to call certain functions to manage and address infection control in our hospital. Recently, a patient in room 404 was diagnosed with a hospital-acquired infection on April 15th, which requires recording as a nosocomial infection. We also aim to evaluate our hand h...
[ { "type": "function", "name": "record_infection_incident", "description": "Records an incident of infection for a patient within the healthcare facility.", "parameters_json": "{\"properties\":{\"affected_area\":{\"description\":\"The area of the healthcare facility where the infection occurred.\",\"...
{ "source_messages": 3, "user_messages": 1, "reasoning_messages": 1, "answer_messages": 0, "tools": 3, "tool_calls": 3, "tool_responses": 0, "terminal_unresolved_calls": 3 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
4
8821ace949e3a6d688b0dd8920c03a9183cf3c5735ec8d00e670739fbca71c02
analysis
analysis_long
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- food_co...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 28, "user_messages": 1, "reasoning_messages": 17, "answer_messages": 1, "tools": 1, "tool_calls": 8, "tool_responses": 8, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
5
855f67d4a46c4371f66bca26a25cb3583c71cc51b6b4a510083cfe550f36442e
analysis
analysis_short
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- ../inpu...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 7, "user_messages": 1, "reasoning_messages": 3, "answer_messages": 1, "tools": 1, "tool_calls": 1, "tool_responses": 1, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
6
cc9162009dec0e69d0b42925e8c32a96a27590a38363beb2a0c8ec49f97cfacb
analysis
analysis_long
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- vgsales...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 19, "user_messages": 1, "reasoning_messages": 11, "answer_messages": 1, "tools": 1, "tool_calls": 5, "tool_responses": 5, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
7
454c5ab04248286c618ee0072f1a3492fe69b8176a4cce642cd1bdb7354efff0
analysis
analysis_long
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- WA_Fn-U...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 19, "user_messages": 1, "reasoning_messages": 11, "answer_messages": 1, "tools": 1, "tool_calls": 5, "tool_responses": 5, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
8
f6fb19c78554e1b8215ad4fb5f4f08b519a1b6672f07e318a70671a16fef4fc0
analysis
analysis_short
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- ../inpu...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 13, "user_messages": 1, "reasoning_messages": 7, "answer_messages": 1, "tools": 1, "tool_calls": 3, "tool_responses": 3, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
10
62596df039f3c00a65d77b5733947c3212b29023046f4caaecfb2b6771d73773
analysis
analysis_long
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- /kaggle...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 19, "user_messages": 1, "reasoning_messages": 11, "answer_messages": 1, "tools": 1, "tool_calls": 5, "tool_responses": 5, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
11
bfce779ed5eafea4bf439bef3e0f57ced81ece03b990bdb5ab43c598a00aab0d
analysis
analysis_short
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- train.c...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 10, "user_messages": 1, "reasoning_messages": 5, "answer_messages": 1, "tools": 1, "tool_calls": 2, "tool_responses": 2, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
12
cd7de30825f7521ffc69870a0ff0a23c91a96dd6bc86f458b14829dfd17d5ac8
analysis
analysis_long
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- Video_G...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 16, "user_messages": 1, "reasoning_messages": 9, "answer_messages": 1, "tools": 1, "tool_calls": 4, "tool_responses": 4, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
13
794b730dface929e6e4e62037b23656dadae4a1fec649e7824666d4fd1701161
analysis
analysis_long
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- aisles....
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 19, "user_messages": 1, "reasoning_messages": 11, "answer_messages": 1, "tools": 1, "tool_calls": 5, "tool_responses": 5, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
14
a2c3ab890920b60398eb946357300654e9cdba89de53e10543dcb34418b5e653
analysis
analysis_long
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- WA_Fn-U...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 16, "user_messages": 1, "reasoning_messages": 9, "answer_messages": 1, "tools": 1, "tool_calls": 4, "tool_responses": 4, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
15
a80ab468c6dbf509511377cbaa4865ffcd9edef5016c32fb4227040277b8ffa0
analysis
analysis_long
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- vgsales...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 16, "user_messages": 1, "reasoning_messages": 9, "answer_messages": 1, "tools": 1, "tool_calls": 4, "tool_responses": 4, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
19
cc800929246fbec5c0c72ec1030095bb6739626cd239f81d0f30cea6fea231eb
generic
function_multi_call
[ { "role": "user", "content": "I have a dataset of customer reviews stored in a JSON file located at `/data/customer_reviews.json`. The dataset includes several reviews, each identified by a'review_id' and containing the text of the review in a'review_text' field. A sample of this dataset looks like this:\n\...
[ { "type": "function", "name": "analyze_sentiment", "description": "Analyzes the sentiment of customer reviews in a JSON file and returns the sentiment for each review.", "parameters_json": "{\"properties\":{\"reviews_json\":{\"description\":\"The file path to the JSON file containing customer review...
{ "source_messages": 3, "user_messages": 1, "reasoning_messages": 1, "answer_messages": 0, "tools": 2, "tool_calls": 2, "tool_responses": 0, "terminal_unresolved_calls": 2 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
21
400ae2f39577109af3755dca975539f8f4fcac3958aba60a3d7593ada14b19ff
analysis
analysis_short
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- winequa...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 10, "user_messages": 1, "reasoning_messages": 5, "answer_messages": 1, "tools": 1, "tool_calls": 2, "tool_responses": 2, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
22
59af9f9adbd6dfdcf3d2199ce20903c5d485923d14214ed6ebf0e115e6718ccf
generic
function_multi_call
[ { "role": "user", "content": "What is the information about the IP address 192.168.1.1 and what are the filtered observations from the last week with ransomware as the first filter and ip as the second filter?", "reasoning_content": null, "tool_call_id": null, "tool_calls": [] }, { "role...
[ { "type": "function", "name": "query", "description": "Queries information about an IP address using the NetDetective API.", "parameters_json": "{\"ipaddress\":{\"default\":\"\",\"description\":\"The IP address to use for the query. Defaults to None, which uses the IP address of the connecting clien...
{ "source_messages": 3, "user_messages": 1, "reasoning_messages": 1, "answer_messages": 0, "tools": 3, "tool_calls": 2, "tool_responses": 0, "terminal_unresolved_calls": 2 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
23
2d596e0f4ea19c2117e5b1a701f296c628ca50cb83eb267a3f53ec6458389f42
analysis
analysis_long
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- train.c...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 16, "user_messages": 1, "reasoning_messages": 9, "answer_messages": 1, "tools": 1, "tool_calls": 4, "tool_responses": 4, "terminal_unresolved_calls": 0 }
reasoning-tool-calling-conversation-v1
Mustafaege/qwen3.5-toolcalling-v2
8f0343a5613879fefda0eb002d10ff7150a2c588
train-00000-of-00002.parquet
b1e65b4fa284f933fbac37a6cca86dcf9544e6fa05a3b57194b6eeb4800f67ed
train
25
4597b229f10fa38f7c5b3a2083606e67e01109d25a82b9611aba2aa6da610f76
analysis
analysis_short
[ { "role": "system", "content": "You are an intelligent data science assistant with access to an stateful jupyter notebook environment you can interact with it using tool calling. For example, you have access to the add_and_execute_jupyter_code_cell tool.\n\nYou have access to the following files:\n- Mall_Cu...
[ { "type": "function", "name": "add_and_execute_jupyter_code_cell", "description": "Add and execute a Python code cell in the stateful Jupyter notebook environment. The notebook retains state across cells, so variables and imports persist.", "parameters_json": "{\"properties\":{\"code\":{\"descriptio...
{ "source_messages": 13, "user_messages": 1, "reasoning_messages": 7, "answer_messages": 1, "tools": 1, "tool_calls": 3, "tool_responses": 3, "terminal_unresolved_calls": 0 }
End of preview. Expand in Data Studio

Reasoning and Tool Calling

This dataset converts tagged reasoning and tool-use conversations into typed messages and tool definitions. It also includes calibration data derived from those converted conversations.

The source is Mustafaege/qwen3.5-toolcalling-v2 at revision 8f0343a5613879fefda0eb002d10ff7150a2c588.

How this differs from the source

The source stores 92,153 train conversations and 10,240 test conversations in a tagged message format. Protocol instructions, tool declarations, reasoning, calls, and tool results can appear inside message text.

This release keeps rows that can be converted to one typed tool-calling schema without guessing about call order, tool identity, or message boundaries. It contains 56,032 train rows and 6,243 test rows.

Property Source This release
Train rows 92,153 56,032
Test rows 10,240 6,243
Message form Tagged text Typed messages with reasoning_content and tool_calls
Tool declarations Embedded in protocol text Structured tools field
Tool arguments Embedded JSON Canonical JSON string
Tool results Tagged text tool messages linked by call identifier
Row identity Source position Source revision, file hash, row number, and content hash
Calibration data Not included 25 rendered histories and four token windows

The conversion does not add conversations. It extracts protocol structure, normalizes the representation, and omits rows whose structure cannot be mapped under the rules below.

A row enters conversations when all of these conditions hold:

  • it contains at least one tool call;
  • tool declarations can be extracted without ambiguity;
  • every called tool has a matching declaration;
  • call arguments contain valid JSON;
  • tool results can be paired with calls in sequence;
  • reasoning and answer text occupy valid positions in that sequence;
  • source-format control tags do not remain after conversion.

The main primary exclusion reasons were:

Primary reason Train Test
Assistant content appears before pending tool results 15,120 1,667
No tool call 10,745 1,176
An unresolved call precedes another call 4,650 534
Embedded tool declarations are ambiguous 2,194 251
Empty tool response 1,378 163
Other tag, JSON, tool-name, or sequence failures 2,034 206
Rows omitted 36,121 3,997

Configurations

Configuration Split Rows Intended use
conversations train 56,032 Training, calibration-candidate selection, or format study
conversations test 6,243 The same conversion applied to the source test split
calibration_histories calibration 25 Inspecting the selected rendered histories and their token IDs
calibration_windows calibration 4 Reusing the exact four 2,048-token calibration windows

The train and test names preserve the source assignments.

Conversation representation

Each row in conversations contains:

  • source dataset, revision, split, file, file SHA-256, row number, and content identity SHA-256;
  • style and tool-call category;
  • typed messages;
  • typed tool declarations;
  • counts for source messages, users, reasoning messages, answers, tools, calls, results, and terminal unresolved calls.

Assistant messages can contain:

  • content for visible answer text;
  • reasoning_content for extracted reasoning;
  • tool_calls with call ID, type, tool name, and arguments_json.

Tool messages carry tool_call_id. Tool declarations contain name, description, and parameters_json.

arguments_json and parameters_json remain strings because argument values and JSON Schema properties have heterogeneous types across tools. Decode them with a JSON parser when object values are needed.

Calibration views

The conversations configuration does not depend on a model tokenizer. The two calibration configurations record a DeepSeek-V4-Flash-0731 rendering and use its tokenizer. They are included for users who need the exact rendered input; other uses should start from conversations.

The calibration view was formed from 25 accepted train histories:

Category Histories
One tool call 9
Multiple tool calls 8
Reasoning with at most three tool calls 5
Reasoning with more than three tool calls 3

The histories were rendered with thinking enabled and DSML tool calls. They were tokenized and concatenated within each category, and one 2,048-token slice was taken from each category stream. calibration_windows contains those four slices, for 8,192 tokens in total.

calibration_histories stores each selected conversation, its rendered prompt, token IDs, category, stream offsets, and content hashes.

calibration_windows stores each slice's token IDs, category, stream offsets, marker counts, selection rule, and contributing history identities. Tokenizer hashes identify the vocabulary used for these token IDs.

License and modifications

The source declares the Apache License 2.0. This release uses the same license.

Downloads last month
45