Skip to content

Instantly share code, notes, and snippets.

@RediAdAstra
RediAdAstra / grpo_demo.py
Created February 18, 2025 20:43 — 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
@RediAdAstra
RediAdAstra / convert_oai_to_sharegpt.py
Created February 18, 2025 20:41 — forked from deepfates/convert_oai_to_sharegpt.py
Convert a fine-tuning dataset from OpenAI format to ShareGPT format
import json
import argparse
def convert_oai_to_sharegpt(input_file: str, output_file: str):
with open(input_file, 'r') as infile, open(output_file, 'w') as outfile:
for line in infile:
conversation = json.loads(line)
# Skip system messages
for message in conversation["messages"]:
if message.get("role") == "system":
@RediAdAstra
RediAdAstra / convert_archive.py
Created November 20, 2024 04:11 — forked from deepfates/convert_archive.py
Convert your twitter archive into a training dataset and markdown files
import argparse
import json
import logging
import os
import re
import shutil
from concurrent.futures import ProcessPoolExecutor, as_completed
from dataclasses import dataclass
from datetime import datetime
from typing import Any, Callable, Dict, List, Literal, Optional, Tuple