Dataset Details
This dataset is a modified version of Anthropic/hh-rlhf
This dataset is used in fine tuning Panther - an state of the art LLM funtuned on llama-7b pretrained model.
A very small portion i.e. 5.3% of prompts and responses were taken from this dataset to finetune and train Panther
Dataset Details
Dataset Structure
Train
Train rows : 377k
Validation
Validation rows : 20.3k
Dataset Format
input : "prompt"
output : "response"
How to Use
from datasets import load_dataset
dataset = load_dataset("Rardilit/Panther-dataset_v1")