Sanskar Shrivastava SanskarX10

🎯

Focusing

deep learning researcher , machine learning @ deepmarinemind

SanskarX10 / grpo_demo.py

Created February 2, 2025 09:08 — 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