domain stringclasses 11
values | source stringclasses 10
values | prompt listlengths 2 200 | completion listlengths 1 1 |
|---|---|---|---|
chat | Nemotron-Cascade-1 | [
{
"content": "You are a helpful and harmless assistant.\n\nYou are not allowed to use any tools.",
"role": "system"
},
{
"content": "A man and his sister jointly purchased a vacation home in California, holding title as joint tenants with the right of survivorship. The man passed away unexpectedly, ... | [
{
"content": "<think>\nWe need to analyze the scenario under California law. The question: A man and his sister jointly purchased a vacation home in California, holding title as joint tenants with the right of survivorship (JTWROS). The man passed away unexpectedly, and his sister sought to transfer the propert... |
conversational_agent | Nemotron-3-Nano | [
{
"content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou cannot do both at the... | [
{
"content": "<think>\nI need to help this user cancel their appointment APPT-5566. They mention it's scheduled for November 12th at 2:00 PM CST, and they're calling 50 hours before the session. According to policy, cancellation fees: >48hr: No fee, 24-48hr: $25 fee, <24hr: Full session charge. 50 hours before ... |
chat | Nemotron-3-Nano | [
{
"content": "",
"role": "system"
},
{
"content": "Solve the following math problem. Make sure to put the answer (and only answer) inside \\boxed{}.\n\nWhen the expression \\((3x^5 + 2x^4 - x + 10)(4x^{12} + 5x^9 - 3x^6 + 20) - (x^3 - 2)^5\\) is expanded, what is the degree of the resulting polynomi... | [
{
"content": "<think>\nWe need to compute the full expanded expression: (3x^5 + 2x^4 - x + 10)(4x^{12} + 5x^9 - 3x^6 + 20) - (x^3 - 2)^5. Need to give all terms in descending powers, confirm constant term, double-check coefficient of x^12 term after subtraction.\n\nWe earlier gave product expansion: let's recom... |
chat | Nemotron-Cascade-1 | [
{
"content": "You are a helpful and harmless assistant.\n\nYou are not allowed to use any tools.",
"role": "system"
},
{
"content": "Answer the following multiple-choice question. At the end of your response, conclude with the sentence `The answer is \\boxed{{X}}.`, replacing X with the correct capi... | [
{
"content": "<think>\nWe need to parse the question: \"According to typical American moral values today, does the main character commit a clearly morally wrong act? Scenario 1 | Larry honestly told his teacher that he didn't see who put the frog in her water bottle, respecting the social norm of not getting hi... |
chat | Nemotron-3-Nano | [
{
"content": "",
"role": "system"
},
{
"content": "I’m working on a small coding challenge and could use your help. \n\n**Task:** \nGiven a list of integers, write a Python program that prints out all pairs of integers from the list that have a difference of 2. The solution must run in O(n log n) ... | [
{
"content": "**Solution Overview**\n\n1. **Sort the list** – `O(n log n)` time. \n After sorting, any two numbers that differ by 2 will appear in the same order as in the original list, which makes the next step easy.\n\n2. **Two‑pointer scan** – `O(n)` time. \n Keep a left pointer `i` and a right pointe... |
chat | Nemotron-Cascade-1 | [
{
"content": "You are a helpful and harmless assistant.\n\nYou are not allowed to use any tools.",
"role": "system"
},
{
"content": "Write a story about a group of friends who start a bookstore.",
"role": "user"
}
] | [
{
"content": "<think>\nThe user asks: \"Write a story about a group of friends who start a bookstore.\"\n\nWe need to produce a story. Likely this should be a narrative with perhaps some description, characters, conflict, resolution.\n\nThe group of friends could be an interesting group: perhaps we could have a... |
conversational_agent | Nemotron-3-Nano | [
{
"content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou cannot do both at the... | [
{
"content": "<think>\nNow I need to provide Maria with the information. She's completed the course with 100% completion and her assessment scores are all above 80% (88, 92, 85), so she's certification eligible. I've requested the certificate and it will be available on June 20th, which matches her deadline. Ac... |
chat | Nemotron-3-Nano | [
{
"content": "",
"role": "system"
},
{
"content": "I just finished setting up a cloud instance to host my online art portfolio and a small blog where I share my pupusa recipes. I need to generate secure login credentials for it so I can start uploading photos of my latest mural projects and recipe v... | [
{
"content": "<think>\nThe user asks for multiple follow-up items. Need to provide JSON? The user didn't explicitly ask for JSON format now, but they said \"walk me through these points\". We should probably keep consistent style: provide JSON with sections for each question. Also include technical details, rec... |
science | Nemotron-Science-v1 | [
{
"content": "",
"role": "system"
},
{
"content": "Answer the following multiple choice question. The last line of your response should be in the following format: 'Answer: A/B/C/D' (e.g. 'Answer: A').\n\nThe relationship between standard reduction potential of a cell and the equilibrium constant is... | [
{
"content": "<think>\nWe need to answer: \"The relationship between standard reduction potential of a cell and the equilibrium constant is shown by: ...\" Options given. We need to recall the Nernst equation and relationship between E° and K. The Nernst equation: E = E° - (RT/nF) ln Q. At equilibrium, E = 0, Q... |
chat | Nemotron-3-Nano | [
{
"content": "",
"role": "system"
},
{
"content": "Write a 4chan greentext story. Write the story in the greentext format like this\n>Be me\n>Be British\n\nUse short sentences, use memes, be funny, be relevant to 4chan culture.",
"role": "user"
},
{
"content": "<think></think>\n>Be me, B... | [
{
"content": "<think>\nOkay, the user wants me to continue a 4chan greentext story about British vs. American biscuit confusion. They've provided a specific continuation where the American brings \"British biscuits\" that turn out to be crackers, and the Brit keeps sobbing \"I'm not a bot.\" \n\nHmm, looking at... |
chat | Nemotron-3-Nano | [
{
"content": "",
"role": "system"
},
{
"content": "I have a short obituary notice that I’d like to turn into a structured JSON object following a specific schema. Here’s the text:\n\n\"He was born on September 30, 1991 in Clarksdale, MS. Christian attended Gautier High School and MGCCC. He was emplo... | [
{
"content": "```json\n{\n \"name\": \"Christian\",\n \"birthDate\": \"1991-09-30\",\n \"birthPlace\": \"Clarksdale, MS\",\n \"education\": [\n \"Gautier High School\",\n \"Mississippi Gulf Coast Community College (MGCCC)\"\n ],\n \"employment\": [\n \"Desoto County Sheriff’s Department\",\n \... |
chat | Nemotron-3-Nano | [
{
"content": "",
"role": "system"
},
{
"content": "Hey there! I'm working on a quick utility for a coding challenge and could use a hand. Could you write a Python function that takes a string as input and returns `True` if the string is a palindrome and `False` otherwise? It should ignore spaces, pu... | [
{
"content": "<think>\nThe user wants a Python function that checks palindrome ignoring spaces, punctuation, capitalization. Provide brief explanation. Should comply with policies. No issues. Provide code with import string or regex. Provide explanation.\n</think>\n**Python palindrome checker**\n\n```python\nim... |
End of preview. Expand in Data Studio
Nemotron-Cascade-2-SFT-Data-Small
A 20% random sample of nvidia/Nemotron-Cascade-2-SFT-Data, merged into a single train split with 4,898,804 rows.
Subsets included (all merged)
| Original subset | Files sampled | ~Rows sampled |
|---|---|---|
| math | math_notool, math_proof, math_tool | ~1,045,266 |
| science | science | ~544,383 |
| chat | chat_part_1 – chat_part_4 | ~2,794,866 |
| instruction_following | instruction_following | ~163,869 |
| safety | safety | ~693 |
| conversational_agent | conversational_agent | ~164,264 |
| swe | swe_agentic, swe_agentless | ~88,174 |
| terminal_agent | terminal_agent | ~97,289 |
Schema
{
"domain": str, # e.g. "math_notool", "chat", "swe_agentic"
"source": str, # upstream data source
"messages": list[{"role": str, "content": str}],
"generator": str, # model that generated the response
}
Usage
from datasets import load_dataset
ds = load_dataset("MaziyarPanahi/Nemotron-Cascade-2-SFT-Data-Small", split="train")
Sampling details
- Sample rate: 20% Bernoulli per source file
- Random seed: 42
- Output format: Parquet (zstd compressed, 500K rows/shard, 10 shards, ~35 GB)
- Downloads last month
- 33