willccbb

# 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

nobuti

CREATE TABLE IF NOT EXISTS `continents` (
  `code` CHAR(2) NOT NULL COMMENT 'Continent code',
  `name` VARCHAR(255),
  PRIMARY KEY (`code`)
) ENGINE=InnoDB;

INSERT INTO `continents` VALUES
  ('AF', 'Africa'),
  ('AS', 'Asia'),
  ('EU', 'Europe'),