Skip to content

Instantly share code, notes, and snippets.

View ChengDobbs's full-sized avatar

ChengDobbs

View GitHub Profile
@ChengDobbs
ChengDobbs / grpo_demo.py
Created March 11, 2025 13:48 — forked from willccbb/grpo_demo.py
GRPO Llama-1B
# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
import re
import torch
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer