Skip to content

Instantly share code, notes, and snippets.

View Leyber91's full-sized avatar
🎯
Focusing

Leyber91

🎯
Focusing
  • Barcelona
View GitHub Profile
@Leyber91
Leyber91 / grpo_demo.py
Created February 3, 2025 05:59 — 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