Skip to content

Instantly share code, notes, and snippets.

View toi500's full-sized avatar

toi500 toi500

View GitHub Profile
@toi500
toi500 / grpo_demo.py
Created January 28, 2025 22:10 — forked from willccbb/grpo_demo.py
GRPO Llama-1B
# train_grpo.py
import re
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer
# Load and prep dataset
SYSTEM_PROMPT = """