Skip to content

Instantly share code, notes, and snippets.

@jpainam
jpainam / grpo_demo.py
Created February 5, 2025 21:51 — forked from willccbb/grpo_demo.py
GRPO Llama-1B
# train_grpo.py
import re
import torch
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer
# Load and prep dataset
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="CompilerConfiguration">
<option name="DEFAULT_COMPILER" value="Javac" />
<resourceExtensions />
<wildcardResourcePatterns>
<entry name="!?*.java" />
<entry name="!?*.form" />
<entry name="!?*.class" />
<entry name="!?*.groovy" />