Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
Previous task error: I/O error: I/O error: Permission denied (os error 13)
Error code: UnexpectedError
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 |
|---|
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
[
{
"role": "user",
"content": "You are an expert evaluation judge specializing in comparative assessment of LLM responses. You are impartial, rigorous, and consistent. Given the conversation context and two assistant responses to the user's latest query, you will follow the evaluation plan and scoring guidel... |
End of preview.
Prompts taken from https://huggingface.co/datasets/nvidia/Nemotron-RLHF-GenRM-v1
Model: nvidia/Gemma-4-31B-IT-NVFP4
Settings:
- Temperature: 1.0
- Top P: 0.95
- Top K: 64
No undisclosed system prompts were used. Messages are exactly as collected -- except that reasoning was processed to remove excessive indentation (shared prefix indentation across all lines), with care to preserve code blocks and general structure.
- Downloads last month
- 86