Skip to content

Instantly share code, notes, and snippets.

View NAB27's full-sized avatar
🏠
Working from home

Nabih Mochir NAB27

🏠
Working from home
View GitHub Profile
@NAB27
NAB27 / grpo_demo.py
Created January 31, 2025 14:14 — 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