Skip to content

Instantly share code, notes, and snippets.

View imeMFK01's full-sized avatar

Muhammad Farhan Khalid imeMFK01

  • Lahore University of Management Sciences (LUMS)
  • Lahore, Pakistan
View GitHub Profile
@imeMFK01
imeMFK01 / grpo_demo.py
Created February 7, 2025 22:26 — 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