Skip to content

Instantly share code, notes, and snippets.

View Arunprakash-A's full-sized avatar

Arun Prakash A Arunprakash-A

View GitHub Profile
@Arunprakash-A
Arunprakash-A / grpo_demo.py
Created April 25, 2025 06:11 — forked from willccbb/grpo_demo.py
GRPO Llama-1B
# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
import re
import torch
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer