Skip to content

Instantly share code, notes, and snippets.

View balqaasem's full-sized avatar
🇵🇸
BalQaasem

Khalifa Al-Sharif balqaasem

🇵🇸
BalQaasem
View GitHub Profile
@balqaasem
balqaasem / grpo_demo.py
Created March 11, 2025 14:36 — 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
@balqaasem
balqaasem / README.md
Last active April 16, 2021 20:54 — forked from webmaster128/README.md
Get started with Substrate on Ubuntu 18.04

Install Substrate

sudo apt update && sudo apt upgrade -y && sudo apt autoremove -y \
  && sudo apt install -y docker.io pwgen jq joe screen \
  && sudo reboot

Now run screen and inside