Skip to content

Instantly share code, notes, and snippets.

@AjaySand
AjaySand / grpo_demo.py
Created January 31, 2025 06:28 — 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
@AjaySand
AjaySand / gist:b16a7f3e73d8e3bb3e89ef78a684f3b7
Created January 20, 2020 17:51 — forked from digitaljhelms/gist:4287848
Git/GitHub branching standards & conventions

Branching

Quick Legend

Description, Instructions, Notes
Instance Branch