This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # 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 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import pandas as pd | |
| import requests | |
| import io | |
| import os | |
| import zipfile | |
| import matplotlib.pyplot as plt | |
| import matplotlib.dates as mdates | |
| import seaborn as sns | |
| import numpy as np |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # | |
| # Panoramix v4 Oct 2019 | |
| # Decompiled source of 0x4f4e0f2cb72E718fC0433222768c57e823162152 | |
| # | |
| # Let's make the world open source | |
| # | |
| # | |
| # I failed with these: | |
| # - unknowna270ef06(?) | |
| # All the rest is below. |