Skip to content

Instantly share code, notes, and snippets.

View jonasdblack's full-sized avatar

Jonas D Black jonasdblack

View GitHub Profile
@jonasdblack
jonasdblack / grpo_demo.py
Created January 30, 2025 22:57 — 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