Gemma Reward-Scored Rollouts Dataset
Generation Parameters
{
"input": {
"source_type": "hf",
"repo_id": "MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-child",
"split": "test",
"path": ""
},"base_dataset": {
"id": "MWilinski/hh-rlhf-harmless-base",
"split": "test",
"prompt_field": "prompt"
},
"selection": {
"prompt_indices": []
},
"scoring": {
"backend": "openrouter",
"model": "google/gemma-3-27b-it"… See the full description on the dataset page:
https://huggingface.co/datasets/MWilinski/hh-rlhf-harmless-base-rollouts-gpt-5.1-child.
