Skip to content

Instantly share code, notes, and snippets.

@apapanto
apapanto / grpo_demo.py
Created January 31, 2025 05:38 — forked from willccbb/grpo_demo.py
GRPO Llama-1B
# 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
@apapanto
apapanto / designer.html
Last active August 29, 2015 14:07
designer
<link href="../core-animated-pages/core-animated-pages.html" rel="import">
<link href="../core-animated-pages/transitions/hero-transition.html" rel="import">
<link href="../core-animated-pages/transitions/cross-fade.html" rel="import">
<link href="../core-animated-pages/transitions/slide-down.html" rel="import">
<link href="../core-animated-pages/transitions/slide-up.html" rel="import">
<link href="../core-animated-pages/transitions/tile-cascade.html" rel="import">
<link href="../core-input/core-input.html" rel="import">
<link href="../core-icon-button/core-icon-button.html" rel="import">
<link href="../core-toolbar/core-toolbar.html" rel="import">
<link href="../core-header-panel/core-header-panel.html" rel="import">