John Shelburne thecatfix

💬

Will reply if u direct mention me on GitHub or Twitter/X.

Former sales guy that had zero coding experience who accidentally bought the IP for a ml platform that identifies bond trade opportunities.

thecatfix / deepseekthis.py

Last active January 31, 2025 02:07 — 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