Datasets:
domain stringclasses 1
value | source stringclasses 1
value | messages listlengths 3 29 | generator stringclasses 1
value |
|---|---|---|---|
conversational_agent | Nemotron-3-Nano | [
{
"role": "system",
"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... | - |
conversational_agent | Nemotron-3-Nano | [
{
"role": "system",
"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... | - |
conversational_agent | Nemotron-3-Nano | [
{
"role": "system",
"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... | - |
conversational_agent | Nemotron-3-Nano | [
{
"role": "system",
"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... | - |
conversational_agent | Nemotron-3-Nano | [
{
"role": "system",
"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... | - |
conversational_agent | Nemotron-3-Nano | [
{
"role": "system",
"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... | - |
conversational_agent | Nemotron-3-Nano | [
{
"role": "system",
"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... | - |
conversational_agent | Nemotron-3-Nano | [
{
"role": "system",
"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... | - |
conversational_agent | Nemotron-3-Nano | [
{
"role": "system",
"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... | - |
conversational_agent | Nemotron-3-Nano | [
{
"role": "system",
"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... | - |
End of preview. Expand in Data Studio
Zenyx V2 — Raw SFT Dataset Collection
This is the unified raw dataset collection used for training Zenyx V2, a custom large language model built from scratch with a novel architecture.
Dataset Sources
| Dataset | Rows | Category |
|---|---|---|
| nemotron_sft_code | 10,108,883 | Code |
| nemotron_sft_math | 22,066,397 | Math |
| nemotron_sft_science | 708,920 | Science |
| nemotron_sft_chat | 39,792 | Chat |
| nemotron_sft_safety | 31,426 | Safety |
| nemotron_rl | 56,339 | Instruction Following (RL) |
| cascade_math | 5,226,364 | Math (Cascade) |
| cascade_science | 2,717,163 | Science (Cascade) |
| cascade_instruction_following | 820,263 | Instruction Following |
| cascade_safety | 3,570 | Safety |
| cascade_conversational_agent | 822,213 | Conversational Agent |
| cascade_swe | 439,610 | Software Engineering |
| cascade_terminal_agent | 485,667 | Terminal Agent |
| redmod_math | 143,055,882 | Math (Thinking + Non-Thinking) |
Column Schemas
Nemotron SFT — input, output, category, license,
reasoning, generator, used_in_training, version, system_prompt
Nemotron Cascade — domain, source, messages, generator
RedMod Math — text
About Zenyx V2
Zenyx is a custom LLM built with a novel architecture featuring:
- Custom tokenizer
- Modified attention mechanism
- Trained entirely on curated open-source data
This dataset is for research purposes. All source datasets retain their original licenses.
Missing (Next Session)
cascade_chat(~200GB, download interrupted)openO1(corrupt JSON issue, fix pending)stepfun_sft(OOM issue, fix pending)
- Downloads last month
- 134