GRPO-Example / app.py
ccdle12's picture
Create app.py
1d59dab verified
raw
history blame contribute delete
251 Bytes
import torch
from datasets import load_dataset
from peft import LoraConfig, get_peft_model
from transformers import AutoModelForCausalLM, AutoTokenizer
from trl import GRPOConfig, GRPOTrainer
dataset = load_dataset("mlabonne/smoltldr")
print(dataset)