paulpessoa
/ grpo_demo.py
Created
February 1, 2025 01:12
— forked from willccbb/grpo_demo.py
GRPO Llama-1B
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 |
paulpessoa
/ instalaciones-react-query.md
Created
March 19, 2024 19:21
— forked from Klerith/instalaciones-react-query.md
Instalaciones recomendadas para el curso de React Query
paulpessoa
/ digitalocean.md
Created
February 19, 2022 01:47
— forked from ofyalcin/$250 DigitalOcean Coupon Code - $250 DigitalOcean Credit - DigitalOcean Promo Code 2023.md
Earn Free $150 DigitalOcean Credit
Hi everyone.
Today I will show you how to earn $100+$50 free credit for digitalocean.
Lets start.
Dont forget, you must have a new account on digitalocean for earn $150 coupon code.