Skip to content

Instantly share code, notes, and snippets.

View aaryanbh96's full-sized avatar

Aryan Bhardwaj aaryanbh96

View GitHub Profile
@aaryanbh96
aaryanbh96 / grpo_demo.py
Created January 30, 2025 23:22 — 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

Running Hadoop

  1. Make a working directory, somewhere
mkdir running-hadoop
cd running-hadoop
  1. Clone the big-data-europe fork for commodity hardware